Relevant bibliographies by topics / State representation learning

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Books
  4. Book chapters
  5. Conference papers
  6. Reports

Academic literature on the topic 'State representation learning'

Author: Grafiati
Published: 25 May 2024
Last updated: 25 January 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'State representation learning.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "State representation learning"

1

Xu, Cai, Wei Zhao, Jinglong Zhao, Ziyu Guan, Yaming Yang, Long Chen, and Xiangyu Song. "Progressive Deep Multi-View Comprehensive Representation Learning." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 9 (June 26, 2023): 10557–65. http://dx.doi.org/10.1609/aaai.v37i9.26254.

Full text
Abstract:
Multi-view Comprehensive Representation Learning (MCRL) aims to synthesize information from multiple views to learn comprehensive representations of data items. Prevalent deep MCRL methods typically concatenate synergistic view-specific representations or average aligned view-specific representations in the fusion stage. However, the performance of synergistic fusion methods inevitably degenerate or even fail when partial views are missing in real-world applications; the aligned based fusion methods usually cannot fully exploit the complementarity of multi-view data. To eliminate all these drawbacks, in this work we present a Progressive Deep Multi-view Fusion (PDMF) method. Considering the multi-view comprehensive representation should contain complete information and the view-specific data contain partial information, we deem that it is unstable to directly learn the mapping from partial information to complete information. Hence, PDMF employs a progressive learning strategy, which contains the pre-training and fine-tuning stages. In the pre-training stage, PDMF decodes the auxiliary comprehensive representation to the view-specific data. It also captures the consistency and complementarity by learning the relations between the dimensions of the auxiliary comprehensive representation and all views. In the fine-tuning stage, PDMF learns the mapping from the original data to the comprehensive representation with the help of the auxiliary comprehensive representation and relations. Experiments conducted on a synthetic toy dataset and 4 real-world datasets show that PDMF outperforms state-of-the-art baseline methods. The code is released at https://github.com/winterant/PDMF.
APA, Harvard, Vancouver, ISO, and other styles
2

Yue, Yang, Bingyi Kang, Zhongwen Xu, Gao Huang, and Shuicheng Yan. "Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 9 (June 26, 2023): 11069–77. http://dx.doi.org/10.1609/aaai.v37i9.26311.

Full text
Abstract:
Deep reinforcement learning (RL) algorithms suffer severe performance degradation when the interaction data is scarce, which limits their real-world application. Recently, visual representation learning has been shown to be effective and promising for boosting sample efficiency in RL. These methods usually rely on contrastive learning and data augmentation to train a transition model, which is different from how the model is used in RL---performing value-based planning. Accordingly, the learned representation by these visual methods may be good for recognition but not optimal for estimating state value and solving the decision problem. To address this issue, we propose a novel method, called value-consistent representation learning (VCR), to learn representations that are directly related to decision-making. More specifically, VCR trains a model to predict the future state (also referred to as the "imagined state'') based on the current one and a sequence of actions. Instead of aligning this imagined state with a real state returned by the environment, VCR applies a Q value head on both of the states and obtains two distributions of action values. Then a distance is computed and minimized to force the imagined state to produce a similar action value prediction as that by the real state. We develop two implementations of the above idea for the discrete and continuous action spaces respectively. We conduct experiments on Atari 100k and DeepMind Control Suite benchmarks to validate their effectiveness for improving sample efficiency. It has been demonstrated that our methods achieve new state-of-the-art performance for search-free RL algorithms.
APA, Harvard, Vancouver, ISO, and other styles
3

de Bruin, Tim, Jens Kober, Karl Tuyls, and Robert Babuska. "Integrating State Representation Learning Into Deep Reinforcement Learning." IEEE Robotics and Automation Letters 3, no. 3 (July 2018): 1394–401. http://dx.doi.org/10.1109/lra.2018.2800101.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Chen, Haoqiang, Yadong Liu, Zongtan Zhou, and Ming Zhang. "A2C: Attention-Augmented Contrastive Learning for State Representation Extraction." Applied Sciences 10, no. 17 (August 26, 2020): 5902. http://dx.doi.org/10.3390/app10175902.

Full text
Abstract:
Reinforcement learning (RL) faces a series of challenges, including learning efficiency and generalization. The state representation used to train RL is one of the important factors causing these challenges. In this paper, we explore providing a more efficient state representation for RL. Contrastive learning is used as the representation extraction method in our work. We propose an attention mechanism implementation and extend an existing contrastive learning method by embedding the attention mechanism. Finally an attention-augmented contrastive learning method called A2C is obtained. As a result, using the state representation from A2C, the robot achieves better learning efficiency and generalization than those using state-of-the-art representations. Moreover, our attention mechanism is proven to be able to calculate the correlation of arbitrary distance among pixels, which is conducive to capturing more accurate obstacle information. What is more, we remove the attention mechanism from A2C. It is shown that the rewards available for the attention-removed A2C are reduced by more than 70%, which indicates the important role of the attention mechanism.
APA, Harvard, Vancouver, ISO, and other styles
5

Ong, Sylvie, Yuri Grinberg, and Joelle Pineau. "Mixed Observability Predictive State Representations." Proceedings of the AAAI Conference on Artificial Intelligence 27, no. 1 (June 30, 2013): 746–52. http://dx.doi.org/10.1609/aaai.v27i1.8680.

Full text
Abstract:
Learning accurate models of agent behaviours is crucial for the purpose of controlling systems where the agents' and environment's dynamics are unknown. This is a challenging problem, but structural assumptions can be leveraged to tackle it effectively. In particular, many systems exhibit mixed observability, when observations of some system components are essentially perfect and noiseless, while observations of other components are imperfect, aliased or noisy. In this paper we present a new model learning framework, the mixed observability predictive state representation (MO-PSR), which extends the previously known predictive state representations to the case of mixed observability systems. We present a learning algorithm that is scalable to large amounts of data and to large mixed observability domains, and show theoretical analysis of the learning consistency and computational complexity. Empirical results demonstrate that our algorithm is capable of learning accurate models, at a larger scale than with the generic predictive state representation, by leveraging the mixed observability properties.
APA, Harvard, Vancouver, ISO, and other styles
6

Maier, Marc, Brian Taylor, Huseyin Oktay, and David Jensen. "Learning Causal Models of Relational Domains." Proceedings of the AAAI Conference on Artificial Intelligence 24, no. 1 (July 3, 2010): 531–38. http://dx.doi.org/10.1609/aaai.v24i1.7695.

Full text
Abstract:
Methods for discovering causal knowledge from observational data have been a persistent topic of AI research for several decades. Essentially all of this work focuses on knowledge representations for propositional domains. In this paper, we present several key algorithmic and theoretical innovations that extend causal discovery to relational domains. We provide strong evidence that effective learning of causal models is enhanced by relational representations. We present an algorithm, relational PC, that learns causal dependencies in a state-of-the-art relational representation, and we identify the key representational and algorithmic innovations that make the algorithm possible. Finally, we prove the algorithm's theoretical correctness and demonstrate its effectiveness on synthetic and real data sets.
APA, Harvard, Vancouver, ISO, and other styles
7

Lesort, Timothée, Natalia Díaz-Rodríguez, Jean-Frano̧is Goudou, and David Filliat. "State representation learning for control: An overview." Neural Networks 108 (December 2018): 379–92. http://dx.doi.org/10.1016/j.neunet.2018.07.006.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Chornozhuk, S. "The New Geometric “State-Action” Space Representation for Q-Learning Algorithm for Protein Structure Folding Problem." Cybernetics and Computer Technologies, no. 3 (October 27, 2020): 59–73. http://dx.doi.org/10.34229/2707-451x.20.3.6.

Full text
Abstract:
Introduction. The spatial protein structure folding is an important and actual problem in computational biology. Considering the mathematical model of the task, it can be easily concluded that finding an optimal protein conformation in a three dimensional grid is a NP-hard problem. Therefore some reinforcement learning techniques such as Q-learning approach can be used to solve the problem. The article proposes a new geometric “state-action” space representation which significantly differs from all alternative representations used for this problem. The purpose of the article is to analyze existing approaches of different states and actions spaces representations for Q-learning algorithm for protein structure folding problem, reveal their advantages and disadvantages and propose the new geometric “state-space” representation. Afterwards the goal is to compare existing and the proposed approaches, make conclusions with also describing possible future steps of further research. Result. The work of the proposed algorithm is compared with others on the basis of 10 known chains with a length of 48 first proposed in [16]. For each of the chains the Q-learning algorithm with the proposed “state-space” representation outperformed the same Q-learning algorithm with alternative existing “state-space” representations both in terms of average and minimal energy values of resulted conformations. Moreover, a plenty of existing representations are used for a 2D protein structure predictions. However, during the experiments both existing and proposed representations were slightly changed or developed to solve the problem in 3D, which is more computationally demanding task. Conclusion. The quality of the Q-learning algorithm with the proposed geometric “state-action” space representation has been experimentally confirmed. Consequently, it’s proved that the further research is promising. Moreover, several steps of possible future research such as combining the proposed approach with deep learning techniques has been already suggested. Keywords: Spatial protein structure, combinatorial optimization, relative coding, machine learning, Q-learning, Bellman equation, state space, action space, basis in 3D space.
APA, Harvard, Vancouver, ISO, and other styles
9

Zhang, Yujia, Lai-Man Po, Xuyuan Xu, Mengyang Liu, Yexin Wang, Weifeng Ou, Yuzhi Zhao, and Wing-Yin Yu. "Contrastive Spatio-Temporal Pretext Learning for Self-Supervised Video Representation." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 3 (June 28, 2022): 3380–89. http://dx.doi.org/10.1609/aaai.v36i3.20248.

Full text
Abstract:
Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these approaches learn representation by discriminating sampled instances via feature similarity in the latent space while ignoring the intermediate state of the learned representations, which limits the overall performance. In this work, taking into account the degree of similarity of sampled instances as the intermediate state, we propose a novel pretext task - spatio-temporal overlap rate (STOR) prediction. It stems from the observation that humans are capable of discriminating the overlap rates of videos in space and time. This task encourages the model to discriminate the STOR of two generated samples to learn the representations. Moreover, we employ a joint optimization combining pretext tasks with contrastive learning to further enhance the spatio-temporal representation learning. We also study the mutual influence of each component in the proposed scheme. Extensive experiments demonstrate that our proposed STOR task can favor both contrastive learning and pretext tasks and the joint optimization scheme can significantly improve the spatio-temporal representation in video understanding. The code is available at https://github.com/Katou2/CSTP.
APA, Harvard, Vancouver, ISO, and other styles
10

Liu, Qiyuan, Qi Zhou, Rui Yang, and Jie Wang. "Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 7 (June 26, 2023): 8843–51. http://dx.doi.org/10.1609/aaai.v37i7.26063.

Full text
Abstract:
Recent work has shown that representation learning plays a critical role in sample-efficient reinforcement learning (RL) from pixels. Unfortunately, in real-world scenarios, representation learning is usually fragile to task-irrelevant distractions such as variations in background or viewpoint. To tackle this problem, we propose a novel clustering-based approach, namely Clustering with Bisimulation Metrics (CBM), which learns robust representations by grouping visual observations in the latent space. Specifically, CBM alternates between two steps: (1) grouping observations by measuring their bisimulation distances to the learned prototypes; (2) learning a set of prototypes according to the current cluster assignments. Computing cluster assignments with bisimulation metrics enables CBM to capture task-relevant information, as bisimulation metrics quantify the behavioral similarity between observations. Moreover, CBM encourages the consistency of representations within each group, which facilitates filtering out task-irrelevant information and thus induces robust representations against distractions. An appealing feature is that CBM can achieve sample-efficient representation learning even if multiple distractions exist simultaneously. Experiments demonstrate that CBM significantly improves the sample efficiency of popular visual RL algorithms and achieves state-of-the-art performance on both multiple and single distraction settings. The code is available at https://github.com/MIRALab-USTC/RL-CBM.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "State representation learning"

1

Nuzzo, Francesco. "Unsupervised state representation pretraining in Reinforcement Learning applied to Atari games." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-288189.

Full text
Abstract:
State representation learning aims to extract useful features from the observations received by a Reinforcement Learning agent interacting with an environment. These features allow the agent to take advantage of the low-dimensional and informative representation to improve the efficiency in solving tasks. In this work, we study unsupervised state representation learning in Atari games. We use a RNN architecture for learning features that depend on sequences of observations, and pretrain a single-frame encoder architecture with different methods on randomly collected frames. Finally, we empirically evaluate how pretrained state representations perform compared with a randomly initialized architecture. For this purpose, we let a RL agent train on 22 different Atari 2600 games initializing the encoder either randomly or with one of the following unsupervised methods: VAE, CPC and ST-DIM. Promising results are obtained in most games when ST-DIM is chosen as pretraining method, while VAE often performs worse than a random initialization.
Tillståndsrepresentationsinlärning handlar om att extrahera användbara egenskaper från de observationer som mottagits av en agent som interagerar med en miljö i förstärkningsinlärning. Dessa egenskaper gör det möjligt för agenten att dra nytta av den lågdimensionella och informativa representationen för att förbättra effektiviteten vid lösning av uppgifter. I det här arbetet studerar vi icke-väglett lärande i Atari-spel. Vi använder en RNN-arkitektur för inlärning av egenskaper som är beroende av observationssekvenser, och förtränar en kodararkitektur för enskild bild med olika metoder på slumpmässigt samlade bilder. Slutligen utvärderar vi empiriskt hur förtränade tillståndsrepresentationer fungerar jämfört med en slumpmässigt initierad arkitektur. För detta ändamål låter vi en RL-agent träna på 22 olika Atari 2600-spel som initierar kodaren antingen slumpmässigt eller med en av följande metoder utan tillsyn: VAE, CPC och ST-DIM. Lovande resultat uppnås i de flesta spel när ST-DIM väljs som metod för träning, medan VAE ofta fungerar sämre än en slumpmässig initialisering.
APA, Harvard, Vancouver, ISO, and other styles
2

Sadeghi, Mohsen. "Representation and interaction of sensorimotor learning processes." Thesis, University of Cambridge, 2018. https://www.repository.cam.ac.uk/handle/1810/278611.

Full text
Abstract:
Human sensorimotor control is remarkably adept at utilising contextual information to learn and recall systematic sensorimotor transformations. Here, we investigate the motor representations that underlie such learning, and examine how motor memories acquired based on different contextual information interact. Using a novel three-dimensional robotic manipulandum, the 3BOT, we examined the spatial transfer of learning across various movement directions in a 3D environment, while human subjects performed reaching movements under velocity-dependent force field. The obtained pattern of generalisation suggested that the representation of dynamic learning was most likely defined in a target-based, rather than an extrinsic, coordinate system. We further examined how motor memories interact when subjects adapt to force fields applied in orthogonal dimensions. We found that, unlike opposing fields, learning two spatially orthogonal force fields led to the formation of separate motor memories, which neither interfered with nor facilitated each other. Moreover, we demonstrated a novel, more general aspect of the spontaneous recovery phenomenon using a two-dimensional force field task: when subjects learned two orthogonal force fields consecutively, in the following phase of clamped error feedback, the expression of adaptation spontaneously rotated from the direction of the second force field, towards the direction of the first force field. Finally, we examined the interaction of sensorimotor memories formed based on separate contextual information. Subjects performed reciprocating reaching and object manipulation tasks under two alternating contexts (movement directions), while we manipulated the dynamics of the task in each context separately. The results suggested that separate motor memories were formed for the dynamics of the task in different contexts, and that these motor memories interacted by sharing error signals to enhance learning. Importantly, the extent of interaction was not fixed between the context-dependent motor memories, but adaptively changed according to the task dynamics to potentially improve overall performance. Together, our experimental and theoretical results add to the understanding of mechanisms that underlie sensorimotor learning, and the way these mechanisms interact under various tasks and different dynamics.
APA, Harvard, Vancouver, ISO, and other styles
3

Merckling, Astrid. "Unsupervised pretraining of state representations in a rewardless environment." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS141.

Full text
Abstract:
Cette thèse vise à étendre les capacités de l'apprentissage de représentation d'état (state representation learning, SRL) afin d'aider la mise à l'échelle des algorithmes d'apprentissage par renforcement profond (deep reinforcement learning, DRL) aux tâches de contrôle continu avec des observations sensorielles à haute dimension (en particulier des images). Le SRL permet d'améliorer les performances des algorithmes de DRL en leur transmettant de meilleures entrées que celles apprises à partir de zéro avec des stratégies de bout-en-bout. Plus précisément, cette thèse aborde le problème de l'estimation d'état à la manière d'un pré-entraînement profond non supervisé de représentations d'état sans récompense. Ces représentations doivent vérifier certaines propriétés pour permettre l'application correcte du bootstrapping et d'autres mécanismes de prises de décisions communs à l'apprentissage supervisé, comme être de faible dimension et garantir la cohérence locale et la topologie (ou connectivité) de l'environnement, ce que nous chercherons à réaliser à travers les modèles pré-entraînés avec les deux algorithmes de SRL proposés dans cette thèse
This thesis seeks to extend the capabilities of state representation learning (SRL) to help scale deep reinforcement learning (DRL) algorithms to continuous control tasks with high-dimensional sensory observations (such as images). SRL allows to improve the performance of DRL by providing it with better inputs than the input embeddings learned from scratch with end-to-end strategies. Specifically, this thesis addresses the problem of performing state estimation in the manner of deep unsupervised pretraining of state representations without reward. These representations must verify certain properties to allow for the correct application of bootstrapping and other decision making mechanisms common to supervised learning, such as being low-dimensional and guaranteeing the local consistency and topology (or connectivity) of the environment, which we will seek to achieve through the models pretrained with the two SRL algorithms proposed in this thesis
APA, Harvard, Vancouver, ISO, and other styles
4

Woodbury, Nathan Scott. "Representation and Reconstruction of Linear, Time-Invariant Networks." BYU ScholarsArchive, 2019. https://scholarsarchive.byu.edu/etd/7402.

Full text
Abstract:
Network reconstruction is the process of recovering a unique structured representation of some dynamic system using input-output data and some additional knowledge about the structure of the system. Many network reconstruction algorithms have been proposed in recent years, most dealing with the reconstruction of strictly proper networks (i.e., networks that require delays in all dynamics between measured variables). However, no reconstruction technique presently exists capable of recovering both the structure and dynamics of networks where links are proper (delays in dynamics are not required) and not necessarily strictly proper.The ultimate objective of this dissertation is to develop algorithms capable of reconstructing proper networks, and this objective will be addressed in three parts. The first part lays the foundation for the theory of mathematical representations of proper networks, including an exposition on when such networks are well-posed (i.e., physically realizable). The second part studies the notions of abstractions of a network, which are other networks that preserve certain properties of the original network but contain less structural information. As such, abstractions require less a priori information to reconstruct from data than the original network, which allows previously-unsolvable problems to become solvable. The third part addresses our original objective and presents reconstruction algorithms to recover proper networks in both the time domain and in the frequency domain.
APA, Harvard, Vancouver, ISO, and other styles
5

Hautot, Julien. "Représentation à base radiale pour l'apprentissage par renforcement visuel." Electronic Thesis or Diss., Université Clermont Auvergne (2021-...), 2024. http://www.theses.fr/2024UCFA0093.

Full text
Abstract:
Ce travail de thèse s'inscrit dans le contexte de l'apprentissage par renforcement (Renforcement Learning - RL) à partir de données image. Contrairement à l'apprentissage supervisé qui permet d'effectuer différentes tâches telles que la classification, la régression ou encore la segmentation à partir d'une base de données annotée, le RL permet d'apprendre, sans base de données, via des interactions avec un environnement. En effet, dans ces méthodes, un agent tel qu'un robot va effectuer différentes actions afin d'explorer son environnement et de récupérer les données d'entraînement. L'entraînement de ce type d'agent s'effectue par essais et erreurs ;lorsque l'agent échoue dans sa tâche, il est pénalisé, tandis que lorsqu'il réussit, il est récompensé. Le but pour l'agent est d'améliorer son comportement pour obtenir le plus de récompenses à long terme. Nous nous intéressons aux extractions visuelles dans des scénarios de RL utilisant des images vues à la première personne. L'utilisation de données visuelles fait souvent appel à des réseaux de convolution profonds permettant de travailler directement sur des images. Cependant, ces réseaux présentent une complexité calculatoire importante, manquent d'explicabilité et souffrent parfois d'instabilité. Pour surmonter ces difficultés, nous avons investigué le développement d'un réseau basé sur des fonctions à base radiales qui permettent des activations éparses et localisées dans l'espace d'entrée. Les réseaux à base radiale (RBFN ) ont connu leur apogée dans les années 90, puis ont été supplantés par les réseaux de convolution car ils étaient jugés difficilement utilisables sur des images en raison de leur coût en calcul. Dans cette thèse, nous avons développé un extracteur de caractéristiques visuelles inspiré des RBFN en simplifiant le coût calculatoire sur les images. Nous avons utilisé notre réseau pour la résolution de tâches visuelles à la première personne et nous avons comparé ses résultats avec différentes méthodes de l'état de l'art; en particulier, des méthodes d'apprentissage de bout-en-bout, des méthodes utilisant l'apprentissage de représentation d'état et des méthodes d'apprentissage machine extrême. Différents scénarios ont été testés issus du simulateur VizDoom, ainsi que du simulateur physique de robotique Pybullet. Outre la comparaison des récompenses obtenues après l'apprentissage, nous avons aussi effectué différents tests sur la robustesse au bruit, la génération des paramètres de notre réseau et le transfert d'une tâche dans la réalité.Le réseau proposé obtient les meilleures performances lors d'apprentissage par renforcement sur les scénarios testés, tout en étant plus simple d'utilisation et d'interprétation. De plus, notre réseau est robuste face à différents bruits, ce qui ouvre la voie à un transfert efficace des connaissances acquises en simulation à la réalité
This thesis work falls within the context of Reinforcement Learning (RL) from image data. Unlike supervised learning, which enables performing various tasks such as classification, regression, or segmentation from an annotated database, RL allows learning without a database through interactions with an environment. In these methods, an agent, such as a robot, performs different actions to explore its environment and gather training data. Training such an agent involves trial and error; the agent is penalized when it fails at its task and rewarded when it succeeds. The goal for the agent is to improve its behavior to obtain the most long-term rewards.We focus on visual extractions in RL scenarios using first-person view images. The use of visual data often involves deep convolutional networks that work directly on images. However, these networks have significant computational complexity, lack interpretability, and sometimes suffer from instability. To overcome these difficulties, we investigated the development of a network based on radial basis functions, which enable sparse and localized activations in the input space. Radial basis function networks (RBFNs) peaked in the 1990s but were later supplanted by convolutional networks due to their high computational cost on images. In this thesis, we developed a visual feature extractor inspired by RBFNs, simplifying the computational cost on images. We used our network for solving first-person visual tasks and compared its results with various state-of-the-art methods, including end-to-end learning methods, state representation learning methods, and extreme machine learning methods. Different scenarios were tested from the VizDoom simulator and the Pybullet robotics physics simulator. In addition to comparing the rewards obtained after learning, we conducted various tests on noise robustness, parameter generation of our network, and task transfer to reality.The proposed network achieves the best performance in reinforcement learning on the tested scenarios while being easier to use and interpret. Additionally, our network is robust to various noise types, paving the way for the effective transfer of knowledge acquired in simulation to reality
APA, Harvard, Vancouver, ISO, and other styles
6

Boots, Byron. "Spectral Approaches to Learning Predictive Representations." Research Showcase @ CMU, 2012. http://repository.cmu.edu/dissertations/131.

Full text
Abstract:
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must obtain an accurate environment model, and then plan to maximize reward. However, for complex domains, specifying a model by hand can be a time consuming process. This motivates an alternative approach: learning a model directly from observations. Unfortunately, learning algorithms often recover a model that is too inaccurate to support planning or too large and complex for planning to succeed; or, they require excessive prior domain knowledge or fail to provide guarantees such as statistical consistency. To address this gap, we propose spectral subspace identification algorithms which provably learn compact, accurate, predictive models of partially observable dynamical systems directly from sequences of action-observation pairs. Our research agenda includes several variations of this general approach: spectral methods for classical models like Kalman filters and hidden Markov models, batch algorithms and online algorithms, and kernel-based algorithms for learning models in high- and infinite-dimensional feature spaces. All of these approaches share a common framework: the model’s belief space is represented as predictions of observable quantities and spectral algorithms are applied to learn the model parameters. Unlike the popular EM algorithm, spectral learning algorithms are statistically consistent, computationally efficient, and easy to implement using established matrixalgebra techniques. We evaluate our learning algorithms on a series of prediction and planning tasks involving simulated data and real robotic systems.
APA, Harvard, Vancouver, ISO, and other styles
7

Gabriel, Florence. "Mental representations of fractions: development, stable state, learning difficulties and intervention." Doctoral thesis, Universite Libre de Bruxelles, 2011. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/209933.

Full text
Abstract:
Fractions are very hard to learn. As the joke goes, “Three out of two people have trouble with fractions”. Yet the invention of a notation for fractions is very ancient, dating back to Babylonians and Egyptians. Moreover, it is thought that ratio representation is innate. And obviously, fractions are part of our everyday life. We read them in recipes, we need them to estimate distances on maps or rebates in shops. In addition, fractions play a key role in science and mathematics, in probabilities, proportions and algebraic reasoning. Then why is it so hard for pupils to understand and use them? What is so special about fractions? As in other areas of numerical cognition, a fast-developing field in cognitive science, we tackled this paradox through a multi-pronged approach, investigating both adults and children.

Based on some recent research questions and intense debates in the literature, a first behavioural study examined the mental representations of the magnitude of fractions in educated adults. Behavioural observations from adults can indeed provide a first clue to explain the paradox raised by fractions. Contrary perhaps to most educated adults’ intuition, finding the value of a given fraction is not an easy operation. Fractions are complex symbols, and there is an on-going debate in the literature about how their magnitude (i.e. value) is processed. In a first study, we asked adult volunteers to decide as quickly as possible whether two fractions represent the same magnitude or not. Equivalent fractions (e.g. 1/4 and 2/8) were identified as representing the same number only about half of the time. In another experiment, adults were also asked to decide which of two fractions was larger. This paradigm offered different results, suggesting that participants relied on both the global magnitude of the fraction and the magnitude of the components. Our results showed that fraction processing depends on experimental conditions. Adults appear to use the global magnitude only in restricted circumstances, mostly with easy and familiar fractions.

In another study, we investigated the development of the mental representations of the magnitude of fractions. Previous studies in adults showed that fraction processing can be either based on the magnitude of the numerators and denominators or based on the global magnitude of fractions and the magnitude of their components. The type of processing depends on experimental conditions. In this experiment, 5th, 6th, 7th-graders, and adults were tested with two paradigms. First, they performed a same/different task. Second, they carried out a numerical comparison task in which they had to decide which of two fractions was larger. Results showed that 5th-graders do not rely on the representations of the global magnitude of fractions in the Numerical Comparison task, but those representations develop from grade 6 until grade 7. In the Same/Different task, participants only relied on componential strategies. From grade 6 on, pupils apply the same heuristics as adults in fraction magnitude comparison tasks. Moreover, we have shown that correlations between global distance effect and children’s general fraction achievement were significant.

Fractions are well known to represent a stumbling block for primary school children. In a third study, we tried to identify the difficulties encountered by primary school pupils. We observed that most 4th and 5th-graders had only a very limited notion of the meaning of fractions, basically referring to pieces of cakes or pizzas. The fraction as a notation for numbers appeared particularly hard to grasp.

Building upon these results, we designed an intervention programme. The intervention “From Pies to Numbers” aimed at improving children’s understanding of fractions as numbers. The intervention was based on various games in which children had to estimate, compare, and combine fractions represented either symbolically or as figures. 20 game sessions distributed over 3 months led to 15-20% improvement in tests assessing children's capacity to estimate and compare fractions; conversely, children in the control group who received traditional lessons improved more in procedural skills such as simplification of fractions and arithmetic operations with fractions. Thus, a short classroom intervention inducing children to play with fractions improved their conceptual understanding.

The results are discussed in light of recent research on the mental representation of the magnitude of fractions and educational theories. The importance of multidisciplinary approaches in psychology and education was also discussed.

In sum, by combining behavioural experiments in adults and children, and intervention studies, we hoped to have improved the understanding how the brain processes mathematical symbols, while helping teachers get a better grasp of pupils’ difficulties and develop classroom activities that suit the needs of learners.


Doctorat en Sciences Psychologiques et de l'éducation
info:eu-repo/semantics/nonPublished

APA, Harvard, Vancouver, ISO, and other styles
8

Shi, Fangzhou. "Towards Molecule Generation with Heterogeneous States via Reinforcement Learning." Thesis, The University of Sydney, 2020. https://hdl.handle.net/2123/22335.

Full text
Abstract:
De novo molecular design and generation are frequently prescribed in the field of chemistry and biology, for it plays a critical role in maintaining the prosperity of the chemical industry and benefiting the drug discovery. Nowadays, many significant problems in this field are based on the philosophy of designing molecular structures towards specific desired properties. This research is very meaningful in both medical and AI fields, which can benefits novel drug discovery for some diseases. However, It remains a challenging task due to the large size of chemical space. In recent years, reinforcement learning-based methods leverage graphs to represent molecules and generate molecules as a decision making process. However, this vanilla graph representation may neglect the intrinsic context information with molecules and limits the generation performance accordingly. In this paper, we propose to augment the original graph states with the SMILES context vectors. As a result, SMILES representations are easily processed by a simple language model such that the general semantic features of a molecule can be extracted; and the graph representations perform better in handling the topology relationship of each atom. Moreover, we propose a framework that combines supervised learning and reinforcement learning algorithm to take a solid consideration of these two heterogeneous state representations of a molecule, which can fuse the information from both of them and extract more comprehensive features so that more sophisticated decisions can be made by the policy network. Our model also introduces two attention mechanisms, i.e., action-attention, and graph-attention, to further improve the performance. We conduct our experiments on a practical dataset, ZINC, and the experiment results demonstrate that our framework can outperform other baselines in the learning performance of molecule generation and chemical property optimization.
APA, Harvard, Vancouver, ISO, and other styles
9

Ford, Shelton J. "The effect of graphing calculators and a three-core representation curriculum on college students' learning of exponential and logarithmic functions." 2008. http://www.lib.ncsu.edu/theses/available/etd-11072008-135009/unrestricted/etd.pdf.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Allen, Heather. "Experiencing literature – learning from experience: the application of neuroscience to literary analysis by example of representations of German colonialism in Uwe Timm’s Morenga." 2011. http://hdl.handle.net/1993/4862.

Full text
Abstract:
Is it probable that a reader can have an empathetic and learning experience of an historical event facilitated through text? Research in neuroscience indicates that the form of a text can trigger mirror neurons, enhancing empathy with the events and characters portrayed and enabling introspective learning through stimulation of the default state network in a reading brain. Narrative elements in historical and fictional literature are analyzed for their potential in facilitating the stimulation of these states. The historical fiction novel Morenga by Uwe Timm is analyzed in order to deduce what a reader neurologically experiences in relation to the text and the historical event portrayed in the novel during the reading process. The probability of the reader experiencing empathy and learning through text so that their perspectives on inter-textual and extra-textual similar events are affected is then developed.
APA, Harvard, Vancouver, ISO, and other styles

Books on the topic "State representation learning"

1

1966-, McBride Kecia Driver, ed. Visual media and the humanities: A pedagogy of representation. Knoxville: University of Tennessee Press, 2004.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
2

Burge, Tyler. Perception: First Form of Mind. Oxford University Press, 2022. http://dx.doi.org/10.1093/oso/9780198871002.001.0001.

Full text
Abstract:
Perception is the first form of representational mind to emerge in evolution. Three types of form are discussed: formal representational structure of perceptual states, formation characteristics in computations of perceptual states, and the form of the visual and visuomotor systems. The book distinguishes perception from non-perceptual sensing. The formal representational structure of perceptual states is developed via a systematic semantics for them—an account of what it is for them to be accurate or inaccurate. This semantics is elaborated by explaining how the representational form is embedded in an iconic format. These structures are then situated in what is known about the processing of perceptual representations, with emphasis on formation of perceptual categorizations. Features of processing that provide insight into the scope of the perceptual (paradigmatically visual) system are highlighted. Relations between these processes and associated perceptual-level capacities—conation, attention, memory, anticipation, affect, learning, imagining—are delineated. Roughly, a perceptual-level capacity is one that borrows its form and content from perception and involves processing that is no more complex or sophisticated than processing that occurs in the classical visual hierarchy. Relations between perception and these associated perceptual-level capacities are argued to occur within the perceptual and perceptual-motor systems. An account of what it is to occur within these systems is elaborated. An upshot is refinement of the distinction between perceptual-level capacities, on one hand, and thought and conception, on the other. Intermediate territory between perception-level representation and propositional thought is explored. The book is resolutely a work in philosophy of science. It attempts to understand perception by focusing on its form, function, and underlying capacities, as indicated in the sciences of perception, rather than by relying on introspection or ordinary talk about perception.
APA, Harvard, Vancouver, ISO, and other styles
3

Boden, Margaret A. 2. General intelligence as the Holy Grail. Oxford University Press, 2018. http://dx.doi.org/10.1093/actrade/9780199602919.003.0002.

Full text
Abstract:
A host of state-of-the-art AI applications exist, designed for countless specific tasks and used in almost every area of life, by laymen and professionals alike. Many outperform even the most expert humans. In that sense, progress has been spectacular. But the AI pioneers were also hoping for systems with general intelligence. ‘General intelligence as the Holy Grail’ explains why artificial general intelligence is still highly elusive despite recent increases in computer power. It considers the general AI strategies in recent research—heuristics, planning, mathematical simplification, and different forms of knowledge representation—and discusses the concepts of the frame problem, agents and distributed cognition, machine learning, and generalist systems.
APA, Harvard, Vancouver, ISO, and other styles
4

Alden, John, Alexander H. Cohen, and Jonathan J. Ring. Gaming the System: Nine Games to Teach American Government Through Active Learning. Taylor & Francis Group, 2019.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
5

Alden, John, Alexander H. Cohen, and Jonathan J. Ring. Gaming the System: Nine Games to Teach American Government Through Active Learning. Taylor & Francis Group, 2019.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
6

Ginsburg, Herbert P., Rachael Labrecque, Kara Carpenter, and Dana Pagar. New Possibilities for Early Mathematics Education. Edited by Roi Cohen Kadosh and Ann Dowker. Oxford University Press, 2014. http://dx.doi.org/10.1093/oxfordhb/9780199642342.013.029.

Full text
Abstract:
Mathematics instruction for young children should begin early, elaborate on and mathematize children’s everyday mathematics, promote a meaningful integration and synthesis of mathematics knowledge, and advance the development of conceptual understanding, procedural fluency, and use of effective strategies. The affordances provided by computer programs can be used to further these goals by involving children in activities that are not possible with traditional methods. Drawing on research and theory concerning the development of mathematical cognition, learning, and teaching, high quality mathematics software can provide a productive learning environment with several components: (1) useful instructions and demonstrations, scaffolds, and feedback; (2) mathematical tools (like a device that groups objects into tens); and (3) virtual objects, manipulatives and mathematical representations. We propose a five-stage iterative research and development process consisting of (1) coherent design; (2) formative research; (3) revision; (4) learning studies; and (5) summative research. A case study ofMathemAntics, software for children ranging from age 3 to grade 3, illustrates the research and development process. The chapter concludes with implications for early childhood educators, software designers, and researchers.
APA, Harvard, Vancouver, ISO, and other styles
7

Rueschemeyer, Shirley-Ann, and M. Gareth Gaskell, eds. The Oxford Handbook of Psycholinguistics. Oxford University Press, 2018. http://dx.doi.org/10.1093/oxfordhb/9780198786825.001.0001.

Full text
Abstract:
This handbook reviews the current state of the art in the field of psycholinguistics. Part I deals with language comprehension at the sublexical, lexical, and sentence and discourse levels. It explores concepts of speech representation and the search for universal speech segmentation mechanisms against a background of linguistic diversity and compares first language with second language segmentation. It also discusses visual word recognition, lexico-semantics, the different forms of lexical ambiguity, sentence comprehension, text comprehension, and language in deaf populations. Part II focuses on language production, with chapters covering topics such as word production and related processes based on evidence from aphasia, the major debates surrounding grammatical encoding. Part III considers various aspects of interaction and communication, including the role of gesture in language processing, approaches to the study of perspective-taking, and the interrelationships between language comprehension, emotion, and sociality. Part IV is concerned with language development and evolution, focusing on topics ranging from the development of prosodic phonology, the neurobiology of artificial grammar learning, and developmental dyslexia. The book concludes with Part V, which looks at methodological advances in psycholinguistic research, such as the use of intracranial electrophysiology in the area of language processing.
APA, Harvard, Vancouver, ISO, and other styles
8

Papafragou, Anna, John C. Trueswell, and Lila R. Gleitman, eds. The Oxford Handbook of the Mental Lexicon. Oxford University Press, 2022. http://dx.doi.org/10.1093/oxfordhb/9780198845003.001.0001.

Full text
Abstract:
The present handbook is a state-of-the-art compilation of papers from leading scholars on the mental lexicon—the representation of language in the mind/brain at the level of individual words and meaningful sub-word units. In recent years, the study of words as mental objects has grown rapidly across several fields including linguistics, psychology, philosophy, neuroscience, education, and computational cognitive science. This comprehensive collection spans multiple disciplines, topics, theories, and methods, to highlight important advances in the study of the mental lexicon, identify areas of debate, and inspire innovation in the field from present and future generations of scholars. The book is divided into three parts. Part I presents modern linguistic and cognitive theories of how the mind/brain represents words at the phonological, morphological, syntactic, semantic, and pragmatic levels. This part also discusses broad architectural issues pertaining to the organization of the lexicon, the relation between words and concepts, and the role of compositionality. Part II discusses how children learn the form and meaning of words in their native language drawing from the key domains of phonology, morphology, syntax, semantics, and pragmatics. Multiple approaches to lexical learning are introduced to explain how learner- and environment-driven factors contribute to both the stability and the variability of lexical learning across both individual learners and communities. Part III examines how the mental lexicon contributes to language use during listening, speaking, and conversation, and includes perspectives from bilingualism, sign languages, and disorders of lexical access and production.
APA, Harvard, Vancouver, ISO, and other styles
9

Caselli, Tommaso, Eduard Hovy, Martha Palmer, and Piek Vossen, eds. Computational Analysis of Storylines. Cambridge University Press, 2021. http://dx.doi.org/10.1017/9781108854221.

Full text
Abstract:
Event structures are central in Linguistics and Artificial Intelligence research: people can easily refer to changes in the world, identify their participants, distinguish relevant information, and have expectations of what can happen next. Part of this process is based on mechanisms similar to narratives, which are at the heart of information sharing. But it remains difficult to automatically detect events or automatically construct stories from such event representations. This book explores how to handle today's massive news streams and provides multidimensional, multimodal, and distributed approaches, like automated deep learning, to capture events and narrative structures involved in a 'story'. This overview of the current state-of-the-art on event extraction, temporal and casual relations, and storyline extraction aims to establish a new multidisciplinary research community with a common terminology and research agenda. Graduate students and researchers in natural language processing, computational linguistics, and media studies will benefit from this book.
APA, Harvard, Vancouver, ISO, and other styles
10

Fox, Roy F. MediaSpeak. Praeger Publishers, 2000. http://dx.doi.org/10.5040/9798400684258.

Full text
Abstract:
This book defines and analyzes the content, structure, and values of three predominant types of public discourse, which are labeled Doublespeak, Salespeak, and Sensationspeak. These media messages are examined to determine how they are constructed and how they influence individuals, ideology, and culture. Discussions are illustrated with a diverse range of examples from popular culture, magazines, Internet sites, politics, television, and film. Fox argues that the Information Age has replaced actual reality with representations of reality. He states that electronic media dominates our lives. Together, these three voices saturate media and technology, profoundly influencing American culture. Fox suggests specific strategies for recognizing and understanding these coded messages. This lively and informative discussion will appeal to anyone who is interested in learning how print and electronic media manipulate both individuals and society as a whole. The extensive research will appeal to media, communications, journalism, and cultural studies scholars alike.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Book chapters on the topic "State representation learning"

1

Merckling, Astrid, Alexandre Coninx, Loic Cressot, Stephane Doncieux, and Nicolas Perrin. "State Representation Learning from Demonstration." In Machine Learning, Optimization, and Data Science, 304–15. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-64580-9_26.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Steccanella, Lorenzo, and Anders Jonsson. "State Representation Learning for Goal-Conditioned Reinforcement Learning." In Machine Learning and Knowledge Discovery in Databases, 84–99. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-26412-2_6.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Schestakov, Stefan, Paul Heinemeyer, and Elena Demidova. "Road Network Representation Learning with Vehicle Trajectories." In Advances in Knowledge Discovery and Data Mining, 57–69. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-33383-5_5.

Full text
Abstract:
AbstractSpatio-temporal traffic patterns reflecting the mobility behavior of road users are essential for learning effective general-purpose road representations. Such patterns are largely neglected in state-of-the-art road representation learning, mainly focusing on modeling road topology and static road features. Incorporating traffic patterns into road network representation learning is particularly challenging due to the complex relationship between road network structure and mobility behavior of road users. In this paper, we present TrajRNE – a novel trajectory-based road embedding model incorporating vehicle trajectory information into road network representation learning. Our experiments on two real-world datasets demonstrate that TrajRNE outperforms state-of-the-art road representation learning baselines on various downstream tasks.
APA, Harvard, Vancouver, ISO, and other styles
4

Sychev, Oleg. "Visualizing Program State as a Clustered Graph for Learning Programming." In Diagrammatic Representation and Inference, 404–7. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-86062-2_41.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Hu, Dapeng, Xuesong Jiang, Xiumei Wei, and Jian Wang. "State Representation Learning for Minimax Deep Deterministic Policy Gradient." In Knowledge Science, Engineering and Management, 481–87. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-29551-6_43.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Meden, Blaž, Abraham Prieto, Peter Peer, and Francisco Bellas. "First Steps Towards State Representation Learning for Cognitive Robotics." In Lecture Notes in Computer Science, 499–510. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-61705-9_41.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Meng, Li, Morten Goodwin, Anis Yazidi, and Paal Engelstad. "Unsupervised State Representation Learning in Partially Observable Atari Games." In Computer Analysis of Images and Patterns, 212–22. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-44240-7_21.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Servan-Schreiber, David, Axel Cleeremans, and James L. McClelland. "Graded State Machines: The Representation of Temporal Contingencies in Simple Recurrent Networks." In Connectionist Approaches to Language Learning, 57–89. Boston, MA: Springer US, 1991. http://dx.doi.org/10.1007/978-1-4615-4008-3_4.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Ding, Ning, Weize Chen, Zhengyan Zhang, Shengding Hu, Ganqu Cui, Yuan Yao, Yujia Qin, et al. "Ten Key Problems of Pre-trained Models: An Outlook of Representation Learning." In Representation Learning for Natural Language Processing, 491–521. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-1600-9_14.

Full text
Abstract:
AbstractThe aforementioned representation learning methods have shown their effectiveness in various NLP scenarios and tasks. Large-scale pre-trained language models (i.e., big models) are the state of the art of representation learning for NLP and beyond. With the rapid growth of data scale and the development of computation devices, big models bring us to a new era of AI and NLP. Standing on the new giants of big models, there are many new challenges and opportunities for representation learning. In the last chapter, we will provide a 2023 outlook for the future directions of representation learning techniques for NLP by summarizing ten key open problems for pre-trained models.
APA, Harvard, Vancouver, ISO, and other styles
10

Li, Zhipeng, and Xuesong Jiang. "State Representation Learning for Multi-agent Deep Deterministic Policy Gradient." In Proceedings of the Fifth Euro-China Conference on Intelligent Data Analysis and Applications, 667–75. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-03766-6_75.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "State representation learning"

1

Li, Ziyi, Xiangtao Hu, Yongle Zhang, and Fujie Zhou. "Task-Oriented Reinforcement Learning with Interest State Representation." In 2024 International Conference on Advanced Robotics and Mechatronics (ICARM), 721–28. IEEE, 2024. http://dx.doi.org/10.1109/icarm62033.2024.10715850.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Drexler, Dominik, Simon Ståhlberg, Blai Bonet, and Hector Geffner. "Symmetries and Expressive Requirements for Learning General Policies." In 21st International Conference on Principles of Knowledge Representation and Reasoning {KR-2023}, 845–55. California: International Joint Conferences on Artificial Intelligence Organization, 2024. http://dx.doi.org/10.24963/kr.2024/79.

Full text
Abstract:
State symmetries play an important role in planning and generalized planning. In the first case, state symmetries can be used to reduce the size of the search; in the second, to reduce the size of the training set. In the case of general planning, however, it is also critical to distinguish non-symmetric states, i.e., states that represent non-isomorphic relational structures. However, while the language of first-order logic distinguishes non-symmetric states, the languages and architectures used to represent and learn general policies do not. In particular, recent approaches for learning general policies use state features derived from description logics or learned via graph neural networks (GNNs) that are known to be limited by the expressive power of C2, first-order logic with two variables and counting. In this work, we address the problem of detecting symmetries in planning and generalized planning and use the results to assess the expressive requirements for learning general policies over various planning domains. For this, we map planning states to plain graphs, run off-the-shelf algorithms to determine whether two states are isomorphic with respect to the goal, and run coloring algorithms to determine if C2 features computed logically or via GNNs distinguish non-isomorphic states. Symmetry detection results in more effective learning, while the failure to detect non-symmetries prevents general policies from being learned at all in certain domains.
APA, Harvard, Vancouver, ISO, and other styles
3

Zhang, Yuanjing, Tao Shang, Chenyi Zhang, and Xueyi Guo. "Quantum Gate Control with State Representation for Deep Reinforcement Learning." In 2024 International Conference on Quantum Communications, Networking, and Computing (QCNC), 119–26. IEEE, 2024. http://dx.doi.org/10.1109/qcnc62729.2024.00028.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Nikolich, Aleksandr, Konstantin Korolev, Sergei Bratchikov, Igor Kiselev, and Artem Shelmanov. "Vikhr: Constructing a State-of-the-art Bilingual Open-Source Instruction-Following Large Language Model for Russian." In Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024), 189–99. Stroudsburg, PA, USA: Association for Computational Linguistics, 2024. http://dx.doi.org/10.18653/v1/2024.mrl-1.15.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Tang, Zhan-Yun, Ya-Rong Liu, and Pan Qin. "Visual Reinforcement Learning Using Dynamic State Representation for Continuous Motion Control." In 2024 43rd Chinese Control Conference (CCC), 8435–40. IEEE, 2024. http://dx.doi.org/10.23919/ccc63176.2024.10662669.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Liu, Junhua, Justin Albrethsen, Lincoln Goh, David Yau, and Kwan Hui Lim. "Spatial-Temporal Graph Representation Learning for Tactical Networks Future State Prediction." In 2024 International Joint Conference on Neural Networks (IJCNN), 1–8. IEEE, 2024. http://dx.doi.org/10.1109/ijcnn60899.2024.10650266.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Shams, Siavash, Sukru Samet Dindar, Xilin Jiang, and Nima Mesgarani. "SSAMBA: Self-Supervised Audio Representation Learning With Mamba State Space Model." In 2024 IEEE Spoken Language Technology Workshop (SLT), 1053–59. IEEE, 2024. https://doi.org/10.1109/slt61566.2024.10832304.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Balyo, Tomáš, Martin Suda, Lukáš Chrpa, Dominik Šafránek, Stephan Gocht, Filip Dvořák, Roman Barták, and G. Michael Youngblood. "Planning Domain Model Acquisition from State Traces without Action Parameters." In 21st International Conference on Principles of Knowledge Representation and Reasoning {KR-2023}, 812–22. California: International Joint Conferences on Artificial Intelligence Organization, 2024. http://dx.doi.org/10.24963/kr.2024/76.

Full text
Abstract:
Existing planning action domain model acquisition approaches consider different types of state traces from which they learn. The differences in state traces refer to the level of observability of state changes (from full to none) and whether the observations have some noise (the state changes might be inaccurately logged). However, to the best of our knowledge, all the existing approaches consider state traces in which each state change corresponds to an action specified by its name and all its parameters (all objects that are relevant to the action). Furthermore, the names and types of all the parameters of the actions to be learned are given. These assumptions are too strong. In this paper, we propose a method that learns action schema from state traces with fully observable state changes but without the parameters of actions responsible for the state changes (only action names are part of the state traces). Although we can easily deduce the number (and names) of the actions that will be in the learned domain model, we still need to deduce the number and types of the parameters of each action alongside its precondition and effects. We show that this task is at least as hard as graph isomorphism. However, our experimental evaluation on a large collection of IPC benchmarks shows that our approach is still practical as the number of required parameters is usually small. Compared to the state-of-the-art learning tools SAM and Extended SAM our new algorithm can provide better results in terms of learning action models more similar to reference models, even though it uses less information and has fewer restrictions on the input traces.
APA, Harvard, Vancouver, ISO, and other styles
9

Parać, Roko, Lorenzo Nodari, Leo Ardon, Daniel Furelos-Blanco, Federico Cerutti, and Alessandra Russo. "Learning Robust Reward Machines from Noisy Labels." In 21st International Conference on Principles of Knowledge Representation and Reasoning {KR-2023}, 909–19. California: International Joint Conferences on Artificial Intelligence Organization, 2024. http://dx.doi.org/10.24963/kr.2024/85.

Full text
Abstract:
This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state ma- chine that decomposes the agent’s task into different sub- tasks. PROB-IRM uses a state-of-the-art inductive logic pro- gramming framework robust to noisy examples to learn RMs from noisy traces using the Bayesian posterior degree of be- liefs, thus ensuring robustness against inconsistencies. Piv- otal for the results is the interleaving between RM learning and policy learning: a new RM is learned whenever the RL agent generates a trace that is believed not to be accepted by the current RM. To speed up the training of the RL agent, PROB-IRM employs a probabilistic formulation of reward shaping that uses the posterior Bayesian beliefs derived from the traces. Our experimental analysis shows that PROB-IRM can learn (potentially imperfect) RMs from noisy traces and exploit them to train an RL agent to solve its tasks success- fully. Despite the complexity of learning the RM from noisy traces, agents trained with PROB-IRM perform comparably to agents provided with handcrafted RMs.
APA, Harvard, Vancouver, ISO, and other styles
10

Zhou, Guichun, and Xiangdong Zhou. "Multivariate Time Series Representation Learning for Electrophysiology Classification with Procedure State Cross-domain Embedding." In 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 1771–74. IEEE, 2024. https://doi.org/10.1109/bibm62325.2024.10822707.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "State representation learning"

1

Babu M.G., Sarath, Debjani Ghosh, Jaideep Gupte, Md Asif Raza, Eric Kasper, and Priyanka Mehra. Kerala’s Grass-roots-led Pandemic Response: Deciphering the Strength of Decentralisation. Institute of Development Studies (IDS), June 2021. http://dx.doi.org/10.19088/ids.2021.049.

Full text
Abstract:
This paper presents an analysis of the role of decentralised institutions to understand the learning and challenges of the grass-roots-led pandemic response of Kerala. The study is based on interviews with experts and frontline workers to ensure the representation of all stakeholders dealing with the outbreak, from the state level to the household level, and a review of published government orders, health guidelines, and news articles. The outcome of the study shows that along with the decentralised system of governance, the strong grass-roots-level network of Accredited Social Health Activists (ASHA) workers, volunteer groups, and Kudumbashree members played a pivotal role in pandemic management in the state. The efficient functioning of local bodies in the state, experience gained from successive disasters, and the Nipah outbreak naturally aided grass-roots-level actions. The lessons others can draw from Kerala are the importance of public expenditure on health, investment for building social capital, and developing the local self-delivery system.
APA, Harvard, Vancouver, ISO, and other styles
2

Iatsyshyn, Anna V., Valeriia O. Kovach, Yevhen O. Romanenko, Iryna I. Deinega, Andrii V. Iatsyshyn, Oleksandr O. Popov, Yulii G. Kutsan, Volodymyr O. Artemchuk, Oleksandr Yu Burov, and Svitlana H. Lytvynova. Application of augmented reality technologies for preparation of specialists of new technological era. [б. в.], February 2020. http://dx.doi.org/10.31812/123456789/3749.

Full text
Abstract:
Augmented reality is one of the most modern information visualization technologies. Number of scientific studies on different aspects of augmented reality technology development and application is analyzed in the research. Practical examples of augmented reality technologies for various industries are described. Very often augmented reality technologies are used for: social interaction (communication, entertainment and games); education; tourism; areas of purchase/sale and presentation. There are various scientific and mass events in Ukraine, as well as specialized training to promote augmented reality technologies. There are following results of the research: main benefits that educational institutions would receive from introduction of augmented reality technology are highlighted; it is determined that application of augmented reality technologies in education would contribute to these technologies development and therefore need increase for specialists in the augmented reality; growth of students' professional level due to application of augmented reality technologies is proved; adaptation features of augmented reality technologies in learning disciplines for students of different educational institutions are outlined; it is advisable to apply integrated approach in the process of preparing future professionals of new technological era; application of augmented reality technologies increases motivation to learn, increases level of information assimilation due to the variety and interactivity of its visual representation. Main difficulties of application of augmented reality technologies are financial, professional and methodical. Following factors are necessary for introduction of augmented reality technologies: state support for such projects and state procurement for development of augmented reality technologies; conduction of scientific research and experimental confirmation of effectiveness and pedagogical expediency of augmented reality technologies application for training of specialists of different specialties; systematic conduction of number of national and international events on dissemination and application of augmented reality technology. It is confirmed that application of augmented reality technologies is appropriate for training of future specialists of new technological era.
APA, Harvard, Vancouver, ISO, and other styles
3

Singh, Abhijeet, Mauricio Romero, and Karthik Muralidharan. COVID-19 Learning Loss and Recovery: Panel Data Evidence from India. Research on Improving Systems of Education (RISE), September 2022. http://dx.doi.org/10.35489/bsg-risewp_2022/112.

Full text
Abstract:
We use a near-representative household panel survey of ∼19,000 primary-school-aged children in rural Tamil Nadu to study the extent of ‘learning loss’ after COVID-19 school closures, the pace of recovery in the months after schools reopened, and the role of a flagship compensatory intervention introduced by the state government. Students tested in December 2021, after 18 months of school closures, displayed severe deficits in learning of about 0.7 standard deviations (σ) in math and 0.34σ in language compared to identically-aged students in the same villages in 2019. Using multiple rounds of in-person testing, we find that two-thirds of this deficit was made up in the 6 months after school reopening. Using value-added models, we attribute ∼24% of the cohort-level recovery to a government-run after-school remediation program which improved test scores for attendees by 0.17σ in math and 0.09σ in Tamil after 3-4 months. Further, while learning loss was regressive, the recovery was progressive, likely reflecting (in part) the greater take up of the remediation program by more socioeconomically disadvantaged students. These positive results from a state-wide program delivered at scale by the government may provide a useful template for both recovery from COVID-19 learning losses, and bridging learning gaps more generally in low-and-middle-income countries.
APA, Harvard, Vancouver, ISO, and other styles
4

Lalisse, Matthias. Measuring the Impact of Campaign Finance on Congressional Voting: A Machine Learning Approach. Institute for New Economic Thinking Working Paper Series, February 2022. http://dx.doi.org/10.36687/inetwp178.

Full text
Abstract:
How much does money drive legislative outcomes in the United States? In this article, we use aggregated campaign finance data as well as a Transformer based text embedding model to predict roll call votes for legislation in the US Congress with more than 90% accuracy. In a series of model comparisons in which the input feature sets are varied, we investigate the extent to which campaign finance is predictive of voting behavior in comparison with variables like partisan affiliation. We find that the financial interests backing a legislator’s campaigns are independently predictive in both chambers of Congress, but also uncover a sizable asymmetry between the Senate and the House of Representatives. These findings are cross-referenced with a Representational Similarity Analysis (RSA) linking legislators’ financial and voting records, in which we show that “legislators who vote together get paid together”, again discovering an asymmetry between the House and the Senate in the additional predictive power of campaign finance once party is accounted for. We suggest an explanation of these facts in terms of Thomas Ferguson’s Investment Theory of Party Competition: due to a number of structural differences between the House and Senate, but chiefly the lower amortized cost of obtaining individuated influence with Senators, political investors prefer operating on the House using the party as a proxy.
APA, Harvard, Vancouver, ISO, and other styles
5

Ferdaus, Md Meftahul, Mahdi Abdelguerfi, Kendall Niles, Ken Pathak, and Joe Tom. Widened attention-enhanced atrous convolutional network for efficient embedded vision applications under resource constraints. Engineer Research and Development Center (U.S.), November 2024. http://dx.doi.org/10.21079/11681/49459.

Full text
Abstract:
Onboard image analysis enables real-time autonomous capabilities for unmanned platforms including aerial, ground, and aquatic drones. Performing classification on embedded systems, rather than transmitting data, allows rapid perception and decision-making critical for time-sensitive applications such as search and rescue, hazardous environment exploration, and military operations. To fully capitalize on these systems’ potential, specialized deep learning solutions are needed that balance accuracy and computational efficiency for time-sensitive inference. This article introduces the widened attention-enhanced atrous convolution-based efficient network (WACEfNet), a new convolutional neural network designed specifically for real-time visual classification challenges using resource-constrained embedded devices. WACEfNet builds on EfficientNet and integrates innovative width-wise feature processing, atrous convolutions, and attention modules to improve representational power without excessive over-head. Extensive benchmarking confirms state-of-the-art performance from WACEfNet for aerial imaging applications while remaining suitable for embedded deployment. The improvements in accuracy and speed demonstrate the potential of customized deep learning advancements to unlock new capabilities for unmanned aerial vehicles and related embedded systems with tight size, weight, and power constraints. This research offers an optimized framework, combining widened residual learning and attention mechanisms, to meet the unique demands of high-fidelity real-time analytics across a variety of embedded perception paradigms.
APA, Harvard, Vancouver, ISO, and other styles
6

Tarasenko, Rostyslav O., Svitlana M. Amelina, Yuliya M. Kazhan, and Olga V. Bondarenko. The use of AR elements in the study of foreign languages at the university. CEUR Workshop Proceedings, November 2020. http://dx.doi.org/10.31812/123456789/4421.

Full text
Abstract:
The article deals with the analysis of the impact of the using AR technology in the study of a foreign language by university students. It is stated out that AR technology can be a good tool for learning a foreign language. The use of elements of AR in the course of studying a foreign language, in particular in the form of virtual excursions, is proposed. Advantages of using AR technology in the study of the German language are identified, namely: the possibility of involvement of different channels of information perception, the integrity of the representation of the studied object, the faster and better memorization of new vocabulary, the development of communicative foreign language skills. The ease and accessibility of using QR codes to obtain information about the object of study from open Internet sources is shown. The results of a survey of students after virtual tours are presented. A reorientation of methodological support for the study of a foreign language at universities is proposed. Attention is drawn to the use of AR elements in order to support students with different learning styles (audio, visual, kinesthetic).
APA, Harvard, Vancouver, ISO, and other styles
7

Tarasenko, Rostyslav O., Svitlana M. Amelina, Yuliya M. Kazhan, and Olga V. Bondarenko. The use of AR elements in the study of foreign languages at the university. CEUR Workshop Proceedings, November 2020. http://dx.doi.org/10.31812/123456789/4421.

Full text
Abstract:
The article deals with the analysis of the impact of the using AR technology in the study of a foreign language by university students. It is stated out that AR technology can be a good tool for learning a foreign language. The use of elements of AR in the course of studying a foreign language, in particular in the form of virtual excursions, is proposed. Advantages of using AR technology in the study of the German language are identified, namely: the possibility of involvement of different channels of information perception, the integrity of the representation of the studied object, the faster and better memorization of new vocabulary, the development of communicative foreign language skills. The ease and accessibility of using QR codes to obtain information about the object of study from open Internet sources is shown. The results of a survey of students after virtual tours are presented. A reorientation of methodological support for the study of a foreign language at universities is proposed. Attention is drawn to the use of AR elements in order to support students with different learning styles (audio, visual, kinesthetic).
APA, Harvard, Vancouver, ISO, and other styles
8

State Legislator Representation: A Data-Driven Learning Guide. Ann Arbor, MI: Inter-university Consortium for Political and Social Research, April 2009. http://dx.doi.org/10.3886/stateleg.

Full text
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'State representation learning' for particular source types:
Journal articles Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography