A Survey of Decision Making in Adversarial Games
Not on the map. Why?
Abstract (arXiv)
Game theory has by now found numerous applications in various fields, including economics, industry, jurisprudence, and artificial intelligence, where each player only cares about its own interest in a noncooperative or cooperative manner, but without obvious malice to other players. However, in many practical applications, such as poker, chess, evader pursuing, drug interdiction, coast guard, cyber-security, and national defense, players often have apparently adversarial stances, that is, selfish actions of each player inevitably or intentionally inflict loss or wreak havoc on other players. Along this line, this paper provides a systematic survey on three main game models widely employed in adversarial games, i.e., zero-sum normal-form and extensive-form games, Stackelberg (security) games, zero-sum differential games, from an array of perspectives, including basic knowledge of game models, (approximate) equilibrium concepts, problem classifications, research frontiers, (approximate) optimal strategy seeking techniques, prevailing algorithms, and practical applications. Finally, promising future research directions are also discussed for relevant adversarial games.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 122 of its 312 references that are in the map. First posted on arXiv 16 Jul 2022.
Builds on
122 of 312 references.
References · 122
- 2016An overview of gradient descent optimization algorithmscited by 1,021
- 2017Generative Adversarial Networks: An Overviewcited by 588
- 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
- 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 228
- 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153
- 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 150
- 2017Cycles in adversarial regularized learningcited by 122
- 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 110
- 2018Deep Counterfactual Regret Minimizationcited by 102
- 2018Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimizationcited by 97
- 2019Open-ended Learning in Symmetric Zero-sum Gamescited by 96
- 2021Near-Optimal No-Regret Learning in General Gamescited by 85
38 more
- 2014Solving Large Imperfect Information Games Using CFR+cited by 78
- 2020Towards Playing Full MOBA Games with Deep Reinforcement Learningcited by 78
- 2020A Game Theoretic Framework for Model Based Reinforcement Learningcited by 72
- 2018Solving Imperfect-Information Games via Discounted Regret Minimizationcited by 68
- 2021Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Gamescited by 66
- 2020Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problemscited by 59
- 2020From Poincar'e Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularizationcited by 59
- 2019A Generalized Training Approach for Multiagent Learningcited by 53
- 2021Adaptive Learning in Continuous Games: Optimal Regret Bounds and Convergence to Nash Equilibriumcited by 51
- 2019α-Rank: Multi-Agent Evaluation by Evolutioncited by 50
- 2020The limits of min-max optimization algorithms: convergence to spurious non-critical setscited by 50
- 2020No-regret learning and mixed Nash equilibria: They do not mixcited by 49
- 2021Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Gamescited by 43
- 2021Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Gamescited by 42
- 2014Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraintscited by 41
- 2021Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Gamescited by 40
- 2017Safe and Nested Subgame Solving for Imperfect-Information Gamescited by 39
- 2022No-Regret Learning in Time-Varying Zero-Sum Gamescited by 36
- 2021Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimizationcited by 34
- 2021Near-optimal Local Convergence of Alternating Gradient Descent-Ascent for Minimax Optimizationcited by 31
- 2022On Last-Iterate Convergence Beyond Zero-Sum Gamescited by 30
- 2019Convergence of Learning Dynamics in Stackelberg Gamescited by 28
- 2021Last-iterate Convergence in Extensive-Form Gamescited by 27
- 2022Near-Optimal Learning of Extensive-Form Games with Imperfect Informationcited by 26
- 2022Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Trainingcited by 26
- 2019Last-iterate convergence rates for min-max optimizationcited by 25
- 2018Depth-Limited Solving for Imperfect-Information Gamescited by 24
- 2021Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recallcited by 21
- 2019Single Deep Counterfactual Regret Minimizationcited by 20
- 2020No-Regret Learning Dynamics for Extensive-Form Correlated Equilibriumcited by 19
- 2022Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Gamescited by 19
- 2016Frank-Wolfe Algorithms for Saddle Point Problemscited by 18
- 2017Computational Results for Extensive-Form Adversarial Team Gamescited by 18
- 2021Online Double Oraclecited by 18
- 2019Coarse Correlation in Extensive-Form Gamescited by 17
- 2020The Advantage Regret-Matching Actor-Criticcited by 17
- 2022Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limitscited by 17
- 2018Double Neural Counterfactual Regret Minimizationcited by 16
50 most cited of 122 All 122 (JSON)
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1.
3 papers.