Zero-Sum Games

Follow this topic Ask about this topic

Zero-sum game research studies how competing players should choose strategies when one player's payoff is the other's loss, with Nash equilibrium and minimax value as central solution concepts. Methods include regret minimization, mirror-descent and best-response learning, self-play reinforcement learning, and value-based approaches for matrix games, stochastic games, and imperfect-information settings. Researchers evaluate strategies using exploitability, regret, and equilibrium gaps, including when data or feedback is limited through offline learning and bandit feedback. A key tension is that algorithms may converge in average behavior but cycle or converge slowly in their final strategies, while stronger guarantees depend on assumptions about feedback, data coverage, and game structure.

Latest papers

45 papers8 papers in the last four weeks, up 167% on the four weeks before. 0.0% of all new papers.

Conservative Policy Iteration For Zero-Sum POSGs
Oct 27, 2026Erwan C. Escudie, Matthia Sabatelli, Jilles Steeve DibangoyePartially Observable Stochastic Games Zero-Sum Games
University of Groningen
Toward Online Robust Zero-Sum Markov Games with Function Approximation
Oct 19, 2026Chenhao Zhou, Jiyu WeiRobust RL Zero-Sum Games
College of Computer Science and Technology, Zhejiang University
IR-PRM+ with Previous-Utility Prediction: Constant Regret and Best-Iterate Convergence
Oct 13, 2026Michael Sullins, Ian A. KashCounterfactual Regret Minimization Regret Minimization
University of Illinois Chicago, Chicago, Illinois, USA
Feedback Dominance Analysis for Pursuit-Evasion Games on Graphs
Oct 5, 2026Yue Guan, Daigo Shishika, Dipankar Maity +2Game Theory Zero-Sum Games
School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA, USA. · College of Engineering and Computing, George Mason University, Fairfax, VA, USA. · Department of Electrical and Computer Engineering, University of North Carolina at Charlotte, Charlotte, NC, USA. +1
Fast Last-Iterate Convergence in Zero-Sum Markov Games with Bandit Feedback
Oct 5, 2026Yuheng ZhangLast-Iterate Convergence Reinforcement Learning
University of Illinois Urbana-Champaign
Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage
Oct 4, 2026Shuze Daniel Liu, Claire Chen, Jiuqi Wang +1Imperfect-Information Games Zero-Sum Games
Massachusetts Institute of Technology · Purdue University · California Institute of Technology +1
$Q$ Can Play That Game: Online Fitted $Q$ -Iteration for Continuous-Action Zero-Sum Markov Games with Convex-Concave Function Approximation
Oct 2, 2026Kushagra Gupta, Jingqi Li, Cade Armstrong +4Zero-Sum Games Game-Theoretic RL
The University of Texas at Austin · The University of California, Berkeley · Massachusetts Institute of Technology (MIT) Lincoln Labs
Average-and Last-Iterate Lower Bounds for Optimistic Matrix Mirror-Prox in Quantum Zero-Sum Games
Sep 30, 2026Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Pucheng XiongLast-Iterate Convergence Oracle Complexity
Department of Computer Sciences, University of Wisconsin-Madison
Minimax Last-Iterate Convergence in Matrix Games with Observed Actions
Sep 28, 2026Yuheng ZhangLast-Iterate Convergence Zero-Sum Games
University of Illinois Urbana-Champaign
Dynamical low-rank equilibrium computation for stochastic games between advanced persistent threats and moving target defense
Sep 20, 2026Tian Zijian, Zhang He, Chen Xinjie +2Nash Equilibrium Computation Zero-Sum Games
College of Control Science and Engineering, Zhejiang University, PC 310027, China · Alibaba Group, Hangzhou, China
Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy
Sep 17, 2026Luis LealNash Equilibrium Self-Play RL
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games
Sep 1, 2026Tomáš Holeček, Viliam LisýImperfect-Information Games Zero-Sum Games
Artificial Intelligence Center, Department of Computer Science Faculty of Electrical Engineering, Czech Technical University in Prague
The concentration game: Bayesian updating, regret, and information
Aug 18, 2026Akshay BalsubramaniMinimax Regret Zero-Sum Games
Distributed Team Orchestration via Supervisor Networks: Convergence, Optimality, and Resilience
Aug 10, 2026Juntian Zhu, Guanpu Chen, Tongtian Zhu +3Multi-Agent Orchestration Zero-Sum Games
School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei 230026, China · School of Automation, Southeast University, Nanjing 210096, China · College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China +2
Beyond the Black Box: Interpretable Models of Human Randomisation Failures
Aug 7, 2026Ngoc Linh DaoInterpretable ML Zero-Sum Games
Alpen-Adria-University of Klagenfurt, Austria
Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation
Jul 30, 2026Boning Li, Longbo HuangImperfect-Information Games Zero-Sum Games
IIIS, Tsinghua University
The Curvature Shadow: An Apparent Failure of Maximum-Entropy Equilibrium Selection is a Removable Artifact
Jul 20, 2026Luis LealNash Equilibrium Imperfect-Information Games
Stability and Convergence of Optimistic Exponential Weights with Asymmetric Step Sizes in Bimatrix Games
Jul 8, 2026Hédi Hadiji, Sarah SachsNash Equilibrium Last-Iterate Convergence
Laboratoire des Signaux et Systèmes, CentraleSupélec, Paris, France · School of Mathematics, University of Bristol, Bristol, United Kingdom
FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games
Jul 7, 2026Chase McDonald, Nathan Tsang, Wesley N. KerrRL Benchmarks Game-Playing Agents
Como Research · Riot Games
Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games
Jul 1, 2026Kevin Wang, Kevin Yang, Arjun Prakash +1Representation Learning Imperfect-Information Games
Brown University
Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process
Jun 27, 2026Congde Hu, Zhuo Jin, Danping Li +1Zero-Sum Games Maximum Entropy RL
School of Mathematics and Statistics, Anhui Normal University, Wuhu, 241002, Anhui, China. · Department of Actuarial Studies and Business Analytics, Macquarie University, Sydney, 2109, NSW, Australia. · School of Statistics, KLATASDS-MOE, China Inclusive Ageing Finance Research Center, East China Normal University, Shanghai, 200062, Shanghai, China.
Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes
Jun 26, 2026Luis LealNash Equilibrium Imperfect-Information Games
EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games
Jun 22, 2026Tristan Maidment, JB Lanier, Chase McDonald +5Self-Play RL Imperfect-Information Games
1Riot Games · 3New York University · University of California, Irvine
GARIP: A Running-Average Moving Reference for Last-Iterate Self-Play in Two-Player Zero-Sum Games
Jun 21, 2026Can SavcıNash Equilibrium Last-Iterate Convergence
Independent Researcher İzmir, Türkiye
A Game-Theoretic Decision Framework for Optimal Selection of Coordination Detection Methods in Multi-UAV Fleet Operations
Jun 1, 2026Christian Manasseh, Savana AmmonsAlgorithm Selection Air Traffic Management
Mobius Logic Inc., Tysons, VA, USA
Fairness in two-player zero-sum games with bandit feedback
May 31, 2026S Akash, Pratik GajaneNash Equilibrium Zero-Sum Games
LatentForce.ai Bengaluru, India · Laboratoire d’Informatique Fondamentale d’Orléans University of Orléans, France
Global Policy-Space Response Oracles for Two-Player Zero-Sum Games
May 27, 2026Junyu Zhang, Feihong Yang, Jian Wang +2Nash Equilibrium Game Theory
Department of Electronic Engineering, Tsinghua University, Beijing, China · Qiyuan Lab, Beijing, China
Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
May 26, 2026Zihao Zheng, Irwin King, Songtao LuGame Theory Zero-Sum Games
Department of Computer Science and Engineering, The Chinese University of Hong Kong · Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong
GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models
May 22, 2026Vartan Shadarevian, Kia Ghods, Alex Kenich +1LLM Evaluation Imperfect-Information Games
Princeton University · Google
Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach
May 19, 2026Yi Feng, Weiming Ou, Xiao WangZero-Sum Games Min-Max Optimization
Aarhus University, Aarhus, Denmark · Shanghai University of Finance and Economics, Shanghai, China · MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics, Shanghai, China

Oct 27, 2026J/K move · Enter open · S save

Conservative Policy Iteration For Zero-Sum POSGs

Erwan C. Escudie, Matthia Sabatelli, Jilles Steeve Dibangoye

University of Groningen

Partially Observable Stochastic Games Zero-Sum Games Policy Iteration Game-Theoretic RL Policy Optimization

Open paper AskPDF arXiv

Occupancy-state reductions make dynamic programming possible for zero-sum partially observable stochastic games (zs-POSGs). Existing point-based solvers usually optimise a central value function. This restores Bellman recursion, but it requires point-based updates over high-dimensional occupancy spaces. We introduce an approximate policy-iteration algorithm for finite-horizon zs-POSGs. The method maintains one policy per player and updates both jointly along occupancy trajectories induced by conservative policy updates. Instead of approximating a full central value function, each update uses a single supporting hyperplane induced by the current joint policy. The algorithm alternates local policy improvements, conservative updates, and persistent exploration. Computation is therefore concentrated on occupancy regions where the current joint policy is exploitable. On finite-horizon zero-sum POSG benchmarks, the method is competitive at small horizons and often improves the runtime-exploitability trade-off at larger horizons compared with PBVI, HSVI, and CFR+.