Log in

Relevant bibliographies by topics / Adversarial games / Journal articles

Journal articles on the topic 'Adversarial games'

To see the other types of publications on this topic, follow the link: Adversarial games.

Author: Grafiati

Published: 10 December 2022

Last updated: 28 January 2023

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

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Adversarial games.'

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.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Alon, Noga, Yuval Emek, Michal Feldman, and Moshe Tennenholtz. "Adversarial Leakage in Games." SIAM Journal on Discrete Mathematics 27, no. 1 (January 2013): 363–85. http://dx.doi.org/10.1137/110858021.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Rosendal, Christian. "Determinacy of adversarial Gowers games." Fundamenta Mathematicae 227, no. 2 (2014): 163–78. http://dx.doi.org/10.4064/fm227-2-3.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Chorppath, Anil Kumar, Tansu Alpcan, and Holger Boche. "Adversarial Behavior in Network Games." Dynamic Games and Applications 5, no. 1 (August 23, 2014): 26–64. http://dx.doi.org/10.1007/s13235-014-0120-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Banks, David, Francesca Petralia, and Shouqiang Wang. "Adversarial risk analysis: Borel games." Applied Stochastic Models in Business and Industry 27, no. 2 (March 2011): 72–86. http://dx.doi.org/10.1002/asmb.890.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Wang, Jiali, Xin Jin, and Yang Tang. "Optimal strategy analysis for adversarial differential games." Electronic Research Archive 30, no. 10 (2022): 3692–710. http://dx.doi.org/10.3934/era.2022189.

Full text

Abstract:

<abstract><p>Optimal decision-making and winning-regions analysis in adversarial differential games are challenging theoretical problems because of the complex interactions between players. To solve these problems, we present an organized review for pursuit-evasion games, reach-avoid games and capture-the-flag games; we also outline recent developments in three types of games. First, we summarize recent results for pursuit-evasion games and classify them according to different numbers of players. As a special kind of pursuit-evasion games, target-attacker-defender games with an active target are analyzed from the perspectives of different speed ratios for players. Second, the related works for reach-avoid games and capture-the-flag games are compared in terms of analytical methods and geometric methods, respectively. These methods have different effects on the barriers and optimal strategy analysis between players. Future directions for the pursuit-evasion games, reach-avoid games, capture-the-flag games and their applications are discussed in the end.</p></abstract>

APA, Harvard, Vancouver, ISO, and other styles

6

Yao, Yuan, Haoxi Zhong, Zhengyan Zhang, Xu Han, Xiaozhi Wang, Kai Zhang, Chaojun Xiao, Guoyang Zeng, Zhiyuan Liu, and Maosong Sun. "Adversarial Language Games for Advanced Natural Language Intelligence." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 16 (May 18, 2021): 14248–56. http://dx.doi.org/10.1609/aaai.v35i16.17676.

Full text

Abstract:

We study the problem of adversarial language games, in which multiple agents with conflicting goals compete with each other via natural language interactions. While adversarial language games are ubiquitous in human activities, little attention has been devoted to this field in natural language processing. In this work, we propose a challenging adversarial language game called Adversarial Taboo as an example, in which an attacker and a defender compete around a target word. The attacker is tasked with inducing the defender to utter the target word invisible to the defender, while the defender is tasked with detecting the target word before being induced by the attacker. In Adversarial Taboo, a successful attacker and defender need to hide or infer the intention, and induce or defend during conversations. This requires several advanced language abilities, such as adversarial pragmatic reasoning and goal-oriented language interactions in open domain, which will facilitate many downstream NLP tasks. To instantiate the game, we create a game environment and a competition platform. Comprehensive experiments on several baseline attack and defense strategies show promising and interesting results, based on which we discuss some directions for future research.

APA, Harvard, Vancouver, ISO, and other styles

7

Garnaev, Andrey, Melike Baykal-Gursoy, and H. Vincent Poor. "Security Games With Unknown Adversarial Strategies." IEEE Transactions on Cybernetics 46, no. 10 (October 2016): 2291–99. http://dx.doi.org/10.1109/tcyb.2015.2475243.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Wu, Yuhang, Sunpreet S. Arora, Yanhong Wu, and Hao Yang. "Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (May 18, 2021): 2969–77. http://dx.doi.org/10.1609/aaai.v35i4.16404.

Full text

Abstract:

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the magnitude of feature variations under multiple perturbations or by measuring its distance from estimated benign example distribution. Instead of using such metrics, the proposed method is based on the observation that the directions of adversarial gradients when crafting (new) adversarial examples play a key role in characterizing the adversarial space. Compared to detection methods that use multiple perturbations, the proposed method is efficient as it only applies a single random perturbation on the input example. Experiments conducted on two different databases, CIFAR-10 and ImageNet, show that the proposed detection method achieves, respectively, 97.9% and 98.6% AUC-ROC (on average) on five different adversarial attacks, and outperforms multiple state-of-the-art detection methods. Results demonstrate the effectiveness of using adversarial gradient directions for adversarial example detection.

APA, Harvard, Vancouver, ISO, and other styles

9

Wampler, Kevin, Erik Andersen, Evan Herbst, Yongjoon Lee, and Zoran Popović. "Character animation in two-player adversarial games." ACM Transactions on Graphics 29, no. 3 (June 2010): 1–13. http://dx.doi.org/10.1145/1805964.1805970.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Rota Bulo, Samuel, Battista Biggio, Ignazio Pillai, Marcello Pelillo, and Fabio Roli. "Randomized Prediction Games for Adversarial Machine Learning." IEEE Transactions on Neural Networks and Learning Systems 28, no. 11 (November 2017): 2466–78. http://dx.doi.org/10.1109/tnnls.2016.2593488.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Polson, Nicholas. "Discussion on ‘Adversarial risk analysis: Borel games’." Applied Stochastic Models in Business and Industry 27, no. 2 (March 2011): 89–91. http://dx.doi.org/10.1002/asmb.892.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

King, Brian, Alan Fern, and Jesse Hostetler. "Adversarial Policy Switching with Application to RTS Games." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 8, no. 3 (June 30, 2021): 14–18. http://dx.doi.org/10.1609/aiide.v8i3.12549.

Full text

Abstract:

Complex games such as RTS games are naturally formalized as Markov games. Given a Markov game, it is often possible to hand-code or learn a set of policies that capture the diversity of possible strategies. It is also often possible to hand-code or learn an abstract simulator of the game that can estimate the outcome of playing two strategies against one another from any state. We consider how to use such policy sets and simulators to make decisions in large Markov games. Prior work has considered the problem using an approach we call minimax policy switching. At each decision epoch, all policy pairs are simulated against each other from the current state, and the minimax policy is chosen and used to select actions until the next decision epoch. While intuitively appealing, we show that this switching policy can have arbitrarily poor worst case performance. In response, we describe a modified algorithm, monotone policy switching, whose worst case performance, under certain conditions, is provably no worse than the minimax fixed policy in the set. We evaluate these switching policies in both a simulated RTS game and the real game Wargus. The results show the effectiveness of policy switching when the simulator is accurate, and also highlight challenges in the face of inaccurate simulations.

APA, Harvard, Vancouver, ISO, and other styles

13

Horčík, Rostislav, Álvaro Torralba, Pavel Rytíř, Lukáš Chrpa, and Stefan Edelkamp. "Optimal Mixed Strategies for Cost-Adversarial Planning Games." Proceedings of the International Conference on Automated Planning and Scheduling 32 (June 13, 2022): 160–68. http://dx.doi.org/10.1609/icaps.v32i1.19797.

Full text

Abstract:

This paper shows that domain-independent tools from classical planning can be used to model and solve a broad class of game-theoretic problems we call Cost-Adversarial Planning Games (CAPGs). We define CAPGs as 2-player normal-form games specified by a planning task and a finite collection of cost functions. The first player (a planning agent) strives to solve a planning task optimally but has limited knowledge about its action costs. The second player (an adversary agent) controls the actual action costs. Even though CAPGs need not be zero-sum, every CAPG has an associated zero-sum game whose Nash equilibrium provides the optimal randomized strategy for the planning agent in the original CAPG. We show how to find the Nash equilibrium of the associated zero-sum game using a cost-optimal planner via the Double Oracle algorithm. To demonstrate the expressivity of CAPGs, we formalize a patrolling security game and several IPC domains as CAPGs.

APA, Harvard, Vancouver, ISO, and other styles

14

Moraes, Rubens, Julian Mariño, and Levi Lelis. "Nested-Greedy Search for Adversarial Real-Time Games." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 14, no. 1 (September 25, 2018): 67–73. http://dx.doi.org/10.1609/aiide.v14i1.13017.

Full text

Abstract:

Churchill and Buro (2013) launched a line of research through Portfolio Greedy Search (PGS), an algorithm for adversarial real-time planning that uses scripts to simplify the problem's action space. In this paper we present a problem in PGS's search scheme that has hitherto been overlooked. Namely, even under the strong assumption that PGS is able to evaluate all actions available to the player, PGS might fail to return the best action. We then describe an idealized algorithm that is guaranteed to return the best action and present an approximation of such algorithm, which we call Nested-Greedy Search (NGS). Empirical results on MicroRTS show that NGS is able to outperform PGS as well as state-of-the-art methods in matches played in small to medium-sized maps.

APA, Harvard, Vancouver, ISO, and other styles

15

Ciftcioglu, Ertugrul Necdet, Siddharth Pal, Kevin S. Chan, Derya H. Cansever, Ananthram Swami, Ambuj K. Singh, and Prithwish Basu. "Topology Design Games and Dynamics in Adversarial Environments." IEEE Journal on Selected Areas in Communications 35, no. 3 (March 2017): 628–42. http://dx.doi.org/10.1109/jsac.2017.2659582.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Laviers, Kennard, and Gita Sukthankar. "A Monte Carlo Approach for Football Play Generation." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 6, no. 1 (October 10, 2010): 150–55. http://dx.doi.org/10.1609/aiide.v6i1.12416.

Full text

Abstract:

Learning effective policies in multi-agent adversarial games is a significant challenge since the search space can be prohibitively large when the actions of all the agents are considered simultaneously. Recent advances in Monte Carlo search methods have produced good results in single-agent games like Go with very large search spaces. In this paper, we propose a variation on the Monte Carlo method, UCT (Upper Confidence Bound Trees), for multi-agent, continuous-valued, adversarial games and demonstrate its utility at generating American football plays for Rush Football 2008. In football, like in many other multi-agent games, the actions of all of the agents are not equally crucial to gameplay success. By automatically identifying key players from historical game play, we can focus the UCT search on player groupings that have the largest impact on yardage gains in a particular formation.

APA, Harvard, Vancouver, ISO, and other styles

17

Buro, Michael, and Santi Ontañón. "Organizers." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 10, no. 2 (June 29, 2021): iii. http://dx.doi.org/10.1609/aiide.v10i2.12737.

Full text

APA, Harvard, Vancouver, ISO, and other styles

18

Kadane, Joseph B. "Adversarial Risk Analysis: What's new, what isn't?: Discussion of Adversarial Risk Analysis: Borel Games." Applied Stochastic Models in Business and Industry 27, no. 2 (March 2011): 87–88. http://dx.doi.org/10.1002/asmb.862.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Deng, Wei, Ze Hui Qu, Li Ye, and Zhi Guang Qin. "A Game Model for Adversarial Classification in Spam Filtering." Advanced Materials Research 433-440 (January 2012): 5053–57. http://dx.doi.org/10.4028/www.scientific.net/amr.433-440.5053.

Full text

Abstract:

With the wide applications of machine learning techniques in spam filtering, malicious adversaries have been increasingly launching attacks against the filtering systems. In this paper, we model the interaction between the data miner and the adversary as Stackelberg games. Though existing algorithms for Stackelberg games efficiently find optimal solutions, they critically assume the follower plays optimally and rationally. Unfortunately, in real-world applications, because of follower's bounded rationality and limited observation of the leader's strategy, it may deviate from their expected optimal response. Considering this crucial problem, this paper solve for the Nash equilibrium. Experiments on real spam dataset demonstrate that bounded rationality and limited observation can make Stackelberg games more practical and provide interesting insights about the interaction between the data miner and the spammer in spam filtering.

APA, Harvard, Vancouver, ISO, and other styles

20

Buro, Michael. "Organizers." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 8, no. 3 (June 30, 2021): iii. http://dx.doi.org/10.1609/aiide.v8i3.12551.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Buro, Michael. "Preface." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 8, no. 3 (June 30, 2021): vii. http://dx.doi.org/10.1609/aiide.v8i3.12550.

Full text

Abstract:

The covered topics in the Adversarial Real-Time Games 2012 AIIDE Workshop range from RTS game unit micro- management (kiting, building unit formations, minimax search for combat), over machine learning approaches to army clustering and strategy improvement, to multi-agent pursuit-evasion and policy switching in RTS games

APA, Harvard, Vancouver, ISO, and other styles

22

Vorobeychik, Yevgeniy, Bo An, Milind Tambe, and Satinder Singh. "Computing Solutions in Infinite-Horizon Discounted Adversarial Patrolling Games." Proceedings of the International Conference on Automated Planning and Scheduling 24 (May 11, 2014): 314–22. http://dx.doi.org/10.1609/icaps.v24i1.13614.

Full text

Abstract:

Stackelberg games form the core of a number of tools deployed for computing optimal patrolling strategies in adversarial domains, such as the US Federal Air Marshall Service and the US Coast Guard. In traditional Stackelberg security game models the attacker knows only the probability that each target is covered by the defender, but is oblivious to the detailed timing of the coverage schedule. In many real-world situations, however, the attacker can observe the current location of the defender and can exploit this knowledge to reason about the defender’s future moves. We show that this general modeling framework can be captured using adversarial patrolling games (APGs) in which the defender sequentially moves between targets, with moves constrained by a graph, while the attacker can observe the defender’s current location and his (stochastic) policy concerning future moves. We offer a very general model of infinite-horizon discounted adversarial patrolling games. Our first contribution is to show that defender policies that condition only on the previous defense move (i.e., Markov stationary policies) can be arbitrarily suboptimal for general APGs. We then offer a mixed-integer non-linear programming (MINLP) formulation for computing optimal randomized policies for the defender that can condition on history of bounded, but arbitrary, length, as well as a mixed-integer linear programming (MILP) formulation to approximate these, with provable quality guarantees. Additionally, we present a non-linear programming (NLP) formulation for solving zero-sum APGs. We show experimentally that MILP significantly outperforms the MINLP formulation, and is, in turn, significantly outperformed by the NLP specialized to zero-sum games.

APA, Harvard, Vancouver, ISO, and other styles

23

Buro, Michael, and Santi Ontañón. "Preface." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 10, no. 2 (June 29, 2021): vii. http://dx.doi.org/10.1609/aiide.v10i2.12738.

Full text

Abstract:

It is our pleasure to present to you the three papers that were accepted for presentation at this second AIIDE workshop on AI for adversarial real-time games, covering building placement optimization, sequential pattern mining for achieving short and long-term goals, and high-level representation for search in RTS games.

APA, Harvard, Vancouver, ISO, and other styles

24

Bown, Oliver, Arne Eigenfeldt, Rania Hodhod, Philippe Pasquier, Reid Swanson, Stephen G. Ware, and Jichen Zhu. "Reports on the 2012 AIIDE Workshops." AI Magazine 34, no. 1 (December 18, 2012): 90. http://dx.doi.org/10.1609/aimag.v34i1.2459.

Full text

Abstract:

The 2012 AIIDE Conference included four workshops: Artificial Intelligence in Adversarial Real-Time Games, Human Computation in Deigital Entertainment and AI for Serious Games, Intelligent Narrative Technologies, and Musican Metacreation. The workshops took place October 8-9, 2012 at Stanford University. This report contains summaries of the activities of those four workshops.

APA, Harvard, Vancouver, ISO, and other styles

25

Stanescu, Marius, Nicolas Barriga, and Michael Buro. "Hierarchical Adversarial Search Applied to Real-Time Strategy Games." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 10, no. 1 (June 29, 2021): 66–72. http://dx.doi.org/10.1609/aiide.v10i1.12714.

Full text

Abstract:

Real-Time Strategy (RTS) video games have proven to be a very challenging application area for artificial intelligence research. Existing AI solutionsare limited by vast state and action spaces and real-time constraints. Most implementations efficiently tackle various tactical or strategic sub-problems, but there is no single algorithm fast enough to be successfully applied to big problem sets (such as a complete instance of the StarCraft RTS game). This paper presents a hierarchical adversarial search framework which more closely models the human way of thinking --- much like the chain of command employed by the military. Each level implements a different abstraction --- from deciding how to win the game at the top of the hierarchy to individual unit orders at the bottom. We apply a 3-layer version of our model to SparCraft ---a StarCraft combat simulator --- and show that it outperforms state of the art algorithms such as Alpha-Beta, UCT, and Portfolio Search in large combat scenarios featuring multiple bases and up to 72 mobile units per player under real-time constraints of 40 ms per search episode.

APA, Harvard, Vancouver, ISO, and other styles

26

Barnes, Tiffany, Oliver Bown, Michael Buro, Michael Cook, Arne Eigenfeldt, Héctor Muñoz-Avila, Santiago Ontañón, et al. "Reports of the Workshops Held at the Tenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment." AI Magazine 36, no. 1 (March 25, 2015): 99–102. http://dx.doi.org/10.1609/aimag.v36i1.2576.

Full text

Abstract:

The AIIDE-14 Workshop program was held Friday and Saturday, October 3–4, 2014 at North Carolina State University in Raleigh, North Carolina. The workshop program included five workshops covering a wide range of topics. The titles of the workshops held Friday were Games and Natural Language Processing, and Artificial Intelligence in Adversarial Real-Time Games. The titles of the workshops held Saturday were Diversity in Games Research, Experimental Artificial Intelligence in Games, and Musical Metacreation. This article presents short summaries of those events.

APA, Harvard, Vancouver, ISO, and other styles

27

Barot, Camille, Michael Buro, Michael Cook, Mirjam Palosaari Eladhari, Boyang “Albert” Li, Antonios Liapis, Magnus Johansson, et al. "The AIIDE 2015 Workshop Program." AI Magazine 37, no. 2 (July 4, 2016): 91–94. http://dx.doi.org/10.1609/aimag.v37i2.2660.

Full text

Abstract:

The workshop program at the Eleventh Annual AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment was held November 14–15, 2015 at the University of California, Santa Cruz, USA. The program included 4 workshops (one of which was a joint workshop): Artificial Intelligence in Adversarial Real-Time Games, Experimental AI in Games, Intelligent Narrative Technologies and Social Believability in Games, and Player Modeling. This article contains the reports of three of the four workshops.

APA, Harvard, Vancouver, ISO, and other styles

28

Chen, Juntao, and Quanyan Zhu. "Control of Multilayer Mobile Autonomous Systems in Adversarial Environments: A Games-in-Games Approach." IEEE Transactions on Control of Network Systems 7, no. 3 (September 2020): 1056–68. http://dx.doi.org/10.1109/tcns.2019.2962316.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Ramanujan, Raghuram, Ashish Sabharwal, and Bart Selman. "On Adversarial Search Spaces and Sampling-Based Planning." Proceedings of the International Conference on Automated Planning and Scheduling 20 (May 25, 2021): 242–45. http://dx.doi.org/10.1609/icaps.v20i1.13437.

Full text

Abstract:

Upper Confidence bounds applied to Trees (UCT), a bandit-based Monte-Carlo sampling algorithm for planning, has recently been the subject of great interest in adversarial reasoning. UCT has been shown to outperform traditional minimax based approaches in several challenging domains such as Go and Kriegspiel, although minimax search still prevails in other domains such as Chess. This work provides insights into the properties of adversarial search spaces that play a key role in the success or failure of UCT and similar sampling-based approaches. We show that certain "early loss" or "shallow trap" configurations, while unlikely in Go, occur surprisingly often in games like Chess (even in grandmaster games). We provide evidence that UCT, unlike minimax search, is unable to identify such traps in Chess and spends a great deal of time exploring much deeper game play than needed.

APA, Harvard, Vancouver, ISO, and other styles

30

Hong, Tzung-Pei, Ke-Yuan Huang, and Wen-Yang Lin. "Adversarial Search by Evolutionary Computation." Evolutionary Computation 9, no. 3 (September 2001): 371–85. http://dx.doi.org/10.1162/106365601750406046.

Full text

Abstract:

In this paper, we consider the problem of finding good next moves in two-player games. Traditional search algorithms, such as minimax and α-β pruning, suffer great temporal and spatial expansion when exploring deeply into search trees to find better next moves. The evolution of genetic algorithms with the ability to find global or near global optima in limited time seems promising, but they are inept at finding compound optima, such as the minimax in a game-search tree. We thus propose a new genetic algorithm-based approach that can find a good next move by reserving the board evaluation values of new offspring in a partial game-search tree. Experiments show that solution accuracy and search speed are greatly improved by our algorithm.

APA, Harvard, Vancouver, ISO, and other styles

31

Justesen, Niels, Tobias Mahlmann, Sebastian Risi, and Julian Togelius. "Playing Multiaction Adversarial Games: Online Evolutionary Planning Versus Tree Search." IEEE Transactions on Games 10, no. 3 (September 2018): 281–91. http://dx.doi.org/10.1109/tciaig.2017.2738156.

Full text

APA, Harvard, Vancouver, ISO, and other styles

32

L'Huillier, Gaston, Richard Weber, and Nicolas Figueroa. "Online phishing classification using adversarial data mining and signaling games." ACM SIGKDD Explorations Newsletter 11, no. 2 (May 27, 2010): 92–99. http://dx.doi.org/10.1145/1809400.1809421.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Banks, David, Francesca Petralia, and Shouqiang Wang. "Rejoinder to the discussion of ‘Adversarial risk analysis: Borel games’." Applied Stochastic Models in Business and Industry 27, no. 2 (March 2011): 92–94. http://dx.doi.org/10.1002/asmb.891.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

You, Yang, Liangwei Li, Baisong Guo, Weiming Wang, and Cewu Lu. "Combinatorial Q-Learning for Dou Di Zhu." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 16, no. 1 (October 1, 2020): 301–7. http://dx.doi.org/10.1609/aiide.v16i1.7445.

Full text

Abstract:

Deep reinforcement learning (DRL) has gained a lot of attention in recent years, and has been proven to be able to play Atari games and Go at or above human levels. However, those games are assumed to have a small fixed number of actions and could be trained with a simple CNN network. In this paper, we study a special class of Asian popular card games called Dou Di Zhu, in which two adversarial groups of agents must consider numerous card combinations at each time step, leading to huge number of actions. We propose a novel method to handle combinatorial actions, which we call combinatorial Q-learning (CQL). We employ a two-stage network to reduce action space and also leverage order-invariant max-pooling operations to extract relationships between primitive actions. Results show that our method prevails over other baseline learning algorithms like naive Q-learning and A3C. We develop an easy-to-use card game environments and train all agents adversarially from sractch, with only knowledge of game rules and verify that our agents are comparative to humans. Our code to reproduce all reported results is available on github.com/qq456cvb/doudizhu-C.

APA, Harvard, Vancouver, ISO, and other styles

35

King, Brian, Alan Fern, and Jesse Hostetler. "On Adversarial Policy Switching with Experiments in Real-Time Strategy Games." Proceedings of the International Conference on Automated Planning and Scheduling 23 (June 2, 2013): 322–26. http://dx.doi.org/10.1609/icaps.v23i1.13602.

Full text

Abstract:

Given a Markov game, it is often possible to hand-code or learn a set of policies that capture a diversity of possible strategies. It is also often possible to hand-code or learn an abstract simulator of the game that can estimate the outcome of playing two strategies against one another from any state. We consider how to use such policy sets and simulators to make decisions in large Markov games such as real-time strategy (RTS) games. Prior work has considered the problem using an approach we call minimax policy switching. At each decision epoch, all policy pairs are simulated against each other from the current state, and the minimax policy is chosen and used to select actions until the next decision epoch. While intuitively appealing, our first contribution is to show that this switching policy can have arbitrarily poor worst case performance. Our second contribution is to describe a simple modification, whose worst case performance is provably no worse than the minimax fixed policy in the set. Our final contribution is to conduct experiments with these algorithms in the domain of RTS games using both an abstract game engine that we can exactly simulate and a real game engine that we can only approximately simulate. The results show the effectiveness of policy switching when the simulator is accurate, and highlight challenges in the face of inaccurate simulations.

APA, Harvard, Vancouver, ISO, and other styles

36

Sun, Lin, Peng Jiao, Kai Xu, Quanjun Yin, and Yabing Zha. "Modified Adversarial Hierarchical Task Network Planning in Real-Time Strategy Games." Applied Sciences 7, no. 9 (August 25, 2017): 872. http://dx.doi.org/10.3390/app7090872.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Nickerson, Jeffrey V. "Adversarial design games and the role of anticipation in sensor networks." Risk and Decision Analysis 1, no. 2 (2009): 75–83. http://dx.doi.org/10.3233/rda-2009-0010.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Figueroa, Nicolas, Gastón L’Huillier, and Richard Weber. "Adversarial classification using signaling games with an application to phishing detection." Data Mining and Knowledge Discovery 31, no. 1 (March 22, 2016): 92–133. http://dx.doi.org/10.1007/s10618-016-0459-9.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Wan, Kaifang, Dingwei Wu, Yiwei Zhai, Bo Li, Xiaoguang Gao, and Zijian Hu. "An Improved Approach towards Multi-Agent Pursuit–Evasion Game Decision-Making Using Deep Reinforcement Learning." Entropy 23, no. 11 (October 29, 2021): 1433. http://dx.doi.org/10.3390/e23111433.

Full text

Abstract:

A pursuit–evasion game is a classical maneuver confrontation problem in the multi-agent systems (MASs) domain. An online decision technique based on deep reinforcement learning (DRL) was developed in this paper to address the problem of environment sensing and decision-making in pursuit–evasion games. A control-oriented framework developed from the DRL-based multi-agent deep deterministic policy gradient (MADDPG) algorithm was built to implement multi-agent cooperative decision-making to overcome the limitation of the tedious state variables required for the traditionally complicated modeling process. To address the effects of errors between a model and a real scenario, this paper introduces adversarial disturbances. It also proposes a novel adversarial attack trick and adversarial learning MADDPG (A2-MADDPG) algorithm. By introducing an adversarial attack trick for the agents themselves, uncertainties of the real world are modeled, thereby optimizing robust training. During the training process, adversarial learning was incorporated into our algorithm to preprocess the actions of multiple agents, which enabled them to properly respond to uncertain dynamic changes in MASs. Experimental results verified that the proposed approach provides superior performance and effectiveness for pursuers and evaders, and both can learn the corresponding confrontational strategy during training.

APA, Harvard, Vancouver, ISO, and other styles

40

Barriga, Nicolas, Marius Stanescu, and Michael Buro. "Puppet Search: Enhancing Scripted Behavior by Look-Ahead Search with Applications to Real-Time Strategy Games." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 11, no. 1 (June 24, 2021): 9–15. http://dx.doi.org/10.1609/aiide.v11i1.12779.

Full text

Abstract:

Real-Time Strategy (RTS) games have shown to be very resilient to standard adversarial tree search techniques. Recently, a few approaches to tackle their complexity have emerged that use game state or move abstractions, or both. Unfortunately, the supporting experiments were either limited to simpler RTS environments (uRTS, SparCraft) or lack testing against state-of-the-art game playing agents. Here, we propose Puppet Search, a new adversarial search framework based on scripts that can expose choice points to a look-ahead search procedure. Selecting a combination of a script and decisions for its choice points represents a move to be applied next. Such moves can be executed in the actual game, thus letting the script play, or in an abstract representation of the game state which can be used by an adversarial tree search algorithm. Puppet Search returns a principal variation of scripts and choices to be executed by the agent for a given time span. We implemented the algorithm in a complete StarCraft bot. Experiments show that it matches or outperforms all of the individual scripts that it uses when playing against state-of-the-art bots from the 2014 AIIDE StarCraft competition.

APA, Harvard, Vancouver, ISO, and other styles

41

Tondi, Benedetta, Neri Merhav, and Mauro Barni. "Detection Games under Fully Active Adversaries." Entropy 21, no. 1 (December 29, 2018): 23. http://dx.doi.org/10.3390/e21010023.

Full text

Abstract:

We study a binary hypothesis testing problem in which a defender must decide whether a test sequence has been drawn from a given memoryless source P 0 , while an attacker strives to impede the correct detection. With respect to previous works, the adversarial setup addressed in this paper considers an attacker who is active under both hypotheses, namely, a fully active attacker, as opposed to a partially active attacker who is active under one hypothesis only. In the fully active setup, the attacker distorts sequences drawn both from P 0 and from an alternative memoryless source P 1 , up to a certain distortion level, which is possibly different under the two hypotheses, to maximize the confusion in distinguishing between the two sources, i.e., to induce both false positive and false negative errors at the detector, also referred to as the defender. We model the defender–attacker interaction as a game and study two versions of this game, the Neyman–Pearson game and the Bayesian game. Our main result is in the characterization of an attack strategy that is asymptotically both dominant (i.e., optimal no matter what the defender’s strategy is) and universal, i.e., independent of P 0 and P 1 . From the analysis of the equilibrium payoff, we also derive the best achievable performance of the defender, by relaxing the requirement on the exponential decay rate of the false positive error probability in the Neyman–Pearson setup and the tradeoff between the error exponents in the Bayesian setup. Such analysis permits characterizing the conditions for the distinguishability of the two sources given the distortion levels.

APA, Harvard, Vancouver, ISO, and other styles

42

Luedtke, Alex, Marco Carone, Noah Simon, and Oleg Sofrygin. "Learning to learn from data: Using deep adversarial learning to construct optimal statistical procedures." Science Advances 6, no. 9 (February 2020): eaaw2140. http://dx.doi.org/10.1126/sciadv.aaw2140.

Full text

Abstract:

Traditionally, statistical procedures have been derived via analytic calculations whose validity often relies on sample size growing to infinity. We use tools from deep learning to develop a new approach, adversarial Monte Carlo meta-learning, for constructing optimal statistical procedures. Statistical problems are framed as two-player games in which Nature adversarially selects a distribution that makes it difficult for a statistician to answer the scientific question using data drawn from this distribution. The players’ strategies are parameterized via neural networks, and optimal play is learned by modifying the network weights over many repetitions of the game. Given sufficient computing time, the statistician’s strategy is (nearly) optimal at the finite observed sample size, rather than in the hypothetical scenario where sample size grows to infinity. In numerical experiments and data examples, this approach performs favorably compared to standard practice in point estimation, individual-level predictions, and interval estimation.

APA, Harvard, Vancouver, ISO, and other styles

43

Chamberland, Simon, and Froduald Kabanza. "Heuristic Planning in Adversarial Dynamic Domains." Proceedings of the AAAI Conference on Artificial Intelligence 25, no. 1 (August 4, 2011): 1766–67. http://dx.doi.org/10.1609/aaai.v25i1.8045.

Full text

Abstract:

Agents in highly dynamic adversarial domains, such as RTS games, must continually make time-critical decisions to adapt their behaviour to the changing environment. In such a context, the planning agent must consider his opponent's actions as uncontrollable, or at best influenceable. In general nondeterministic domains where there is no clear turn-taking protocol, most heuristic search methods to date do not explicitly reason about the opponent's actions when guiding the state space exploration towards goal or high-reward states. In contrast, we are investigating a domain-independent heuristic planning approach which reasons about the dynamics and uncontrollability of the opponent's behaviours in order to provide better guidance to the search process of the planner. Our planner takes as input the opponent's behaviours recognized by a plan recognition module and uses them to identify opponent's actions that lead to low-utility projected states. We believe such explicit heuristic reasoning about the potential behaviours of the opponent is crucial when planning in adversarial domains, yet is missing in today's planning approaches.

APA, Harvard, Vancouver, ISO, and other styles

44

Bohrer, Brandon, and André Platzer. "Structured Proofs for Adversarial Cyber-Physical Systems." ACM Transactions on Embedded Computing Systems 20, no. 5s (October 31, 2021): 1–26. http://dx.doi.org/10.1145/3477024.

Full text

Abstract:

Many cyber-physical systems (CPS) are safety-critical, so it is important to formally verify them, e.g. in formal logics that show a model’s correctness specification always holds. Constructive Differential Game Logic ( CdGL ) is such a logic for (constructive) hybrid games, including hybrid systems. To overcome undecidability, the user first writes a proof, for which we present a proof-checking tool. We introduce Kaisar , the first language and tool for CdGL proofs, which until now could only be written by hand with a low-level proof calculus. Kaisar’s structured proofs simplify challenging CPS proof tasks, especially by using programming language principles and high-level stateful reasoning. Kaisar exploits CdGL ’s constructivity and refinement relations to build proofs around models of game strategies. The evaluation reproduces and extends existing case studies on 1D and 2D driving. Proof metrics are compared and reported experiences are discussed for the original studies and their reproductions.

APA, Harvard, Vancouver, ISO, and other styles

45

Plakhotnik, O. V. "THEORY OF GAMES IN THE CRIMINAL PROCESS OF UKRAINE." Criminalistics and Forensics, no. 64 (May 7, 2019): 294–305. http://dx.doi.org/10.33994/kndise.2019.64.26.

Full text

Abstract:

The purpose of this article is to reveal the possibility of using game theory in the criminal process of Ukraine. The article deals with the adversarial principle of the criminal proceedings. The presence of conflicting interests of both sides gives rise to the procedural interests of each of them. Defending legal positions with due regard for procedural interests leads to rational behavior of the both sides. Such activities can be called strategic, and the process of achieving the interests of the both sides in criminal proceedings is the strategy of the sides to criminal proceedings. Both sides in criminal proceedings will develop optimal strategies for achieving the appropriate procedural goal. The choice of the optimal strategy of the prosecution or the defense allows you to use game theory, as the theory of mathematical models for making optimal decisions in the context of a divergence of interests of the both sides in criminal proceedings. The article provides a definition of strategy and a definition of Game Theory. Conflicts that are considered in game theory are compared by analogy with a dispute in a criminal proceeding. The work of B.D. Leonov “The role of the theory of strategic behavior (game theory) in the regulation of the fight against terrorism” about the fact that game theory helps to choose the best strategies, taking into account ideas about other participants, their resources and possible actions. The work of A.A. Shiyan “Game Theory: Basics and Applications in Economics and Management” about the need to master the skills and abilities to apply game theory. The work of O.Y. Baev “Selected Works on the Problems of Criminalistics and Criminal Procedure” about the fact that, from the standpoint of the categorical apparatus of game theory, the adversarial principle completely fits into the so-called antagonistic game of two players. It was analyzed the work of O.G. Yanovskaja “Effective implementation of the functions of the prosecution and defense as a condition of adversary criminal proceedings” about the strategy and tactics of advocacy from the perspective of using the concept of solving game theory. It was analyzed the work of Y.A. Tsvetkov “The game of justice: How to increase the gain?” which examines the practical application of game theory in criminal proceedings using the Nash matrix and algorithms for making optimal decisions. It is concluded that the adversarial principle can be applied using ready-made mathematical models to make optimal decisions in criminal proceedings in order to achieve Nash equilibrium and, in general, increase the predictability of the outcome of criminal proceedings. Key words: game theory, criminal proceedings.

APA, Harvard, Vancouver, ISO, and other styles

46

Leece, Michael. "Unsupervised Learning of HTNs in Complex Adversarial Domains." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 10, no. 6 (June 29, 2021): 6–9. http://dx.doi.org/10.1609/aiide.v10i6.12697.

Full text

Abstract:

While Hierarchical Task Networks are frequently cited as flexible and powerful planning models, they are often ignored due to the intensive labor cost for experts/programmers, due to the need to create and refine the model by hand. While recent work has begun to address this issue by working towards learning aspects of an HTN model from demonstration, or even the whole framework, the focus so far has been on simple toy domains, which lack many of the challenges faced in the real world such as imperfect information and continuous environments. I plan to extend this work using the domain of real-time strategy (RTS) games, which have gained recent popularity as a challenging and complex domain for AI research.

APA, Harvard, Vancouver, ISO, and other styles

47

Jaidee, Ulit, and Hector Munoz-Avila. "CLASSQ-L: A Q-Learning Algorithm for Adversarial Real-Time Strategy Games." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 8, no. 3 (June 30, 2021): 8–13. http://dx.doi.org/10.1609/aiide.v8i3.12547.

Full text

Abstract:

We present CLASSQ-L (for: class Q-learning) an application of the Q-learning reinforcement learning algorithm to play complete Wargus games. Wargus is a real-time strategy game where players control armies consisting of units of different classes (e.g., archers, knights). CLASSQ-L uses a single table for each class of unit so that each unit is controlled and updates its class’ Q-table. This enables rapid learning as in Wargus there are many units of the same class. We present initial results of CLASSQ-L against a variety of opponents.

APA, Harvard, Vancouver, ISO, and other styles

48

Sengupta, S., S. Anand, K. Hong, and R. Chandramouli. "On Adversarial Games in Dynamic Spectrum Access Networking based Covert Timing Channels?" ACM SIGMOBILE Mobile Computing and Communications Review 13, no. 2 (September 25, 2009): 96–107. http://dx.doi.org/10.1145/1621076.1621086.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Casey, William, Rhiannon Weaver, Jose Andre Morales, Evan Wright, and Bud Mishra. "Epistatic Signaling and Minority Games, the Adversarial Dynamics in Social Technological Systems." Mobile Networks and Applications 21, no. 1 (February 2016): 161–74. http://dx.doi.org/10.1007/s11036-016-0705-9.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Chao, Rui, Ben W. Reichardt, Chris Sutherland, and Thomas Vidick. "Test for a large amount of entanglement, using few measurements." Quantum 2 (September 3, 2018): 92. http://dx.doi.org/10.22331/q-2018-09-03-92.

Full text

Abstract:

Bell-inequality violations establish that two systems share some quantum entanglement. We give a simple test to certify that two systems share an asymptotically large amount of entanglement,nEPR states. The test is efficient: unlike earlier tests that play many games, in sequence or in parallel, our test requires only one or two CHSH games. One system is directed to play a CHSH game on a random specified qubiti, and the other is told to play games on qubits{i,j}, without knowing which index isi.The test is robust: a success probability withinδof optimal guarantees distanceO(n5/2δ)fromnEPR states. However, the test does not tolerate constantδ; it breaks down forδ=Ω~(1/n). We give an adversarial strategy that succeeds within delta of the optimum probability using onlyO~(δ−2)EPR states.

APA, Harvard, Vancouver, ISO, and other styles

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!