{"total":78,"rows":[{"id":"2310.18940","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game","created":"2023-10-29","cited_by_count":152,"area":"agents"},{"id":"2309.17277","title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","created":"2023-09-29","cited_by_count":68,"area":"agents"},{"id":"2206.05825","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","created":"2022-06-12","cited_by_count":66,"area":null},{"id":"2103.06426","title":"XDO: A Double Oracle Algorithm for Extensive-Form Games","created":"2021-03-11","cited_by_count":34,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2106.14326","title":"Last-iterate Convergence in Extensive-Form Games","created":"2021-06-27","cited_by_count":28,"area":null},{"id":"2202.01752","title":"Near-Optimal Learning of Extensive-Form Games with Imperfect Information","created":"2022-02-03","cited_by_count":26,"area":null},{"id":"2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","created":"2024-08-02","cited_by_count":26,"area":"deeprl"},{"id":"2104.01520","title":"Simple Uncoupled No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium","created":"2021-04-04","cited_by_count":22,"area":null},{"id":"2106.06279","title":"Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall","created":"2021-06-11","cited_by_count":21,"area":null},{"id":"2102.06973","title":"Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games","created":"2021-02-13","cited_by_count":15,"area":null},{"id":"2502.04686","title":"Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization","created":"2025-02-07","cited_by_count":15,"area":"agents"},{"id":"2305.14709","title":"Regret Matching+: (In)Stability and Fast Convergence in Games","created":"2023-05-24","cited_by_count":14,"area":null},{"id":"2502.08938","title":"Reevaluating Policy Gradient Methods for Imperfect-Information Games","created":"2025-02-13","cited_by_count":13,"area":"deeprl"},{"id":"2103.04539","title":"Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games","created":"2021-03-08","cited_by_count":12,"area":null},{"id":"2212.12567","title":"Adapting to game trees in zero-sum imperfect information games","created":"2022-12-23","cited_by_count":11,"area":null},{"id":"2403.04344","title":"RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning","created":"2024-03-07","cited_by_count":10,"area":"deeprl"},{"id":"2305.16610","title":"Adaptively Perturbed Mirror Descent for Learning in Games","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2111.05884","title":"Search in Imperfect Information Games","created":"2021-11-10","cited_by_count":8,"area":null},{"id":"2206.09254","title":"Mutation-Driven Follow the Regularized Leader for Last-Iterate Convergence in Zero-Sum Games","created":"2022-06-18","cited_by_count":8,"area":null},{"id":"2210.14640","title":"HSVI can solve zero-sum Partially Observable Stochastic Games","created":"2022-10-26","cited_by_count":8,"area":null},{"id":"2506.03464","title":"From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications","created":"2025-06-04","cited_by_count":8,"area":null},{"id":"2206.09161","title":"A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving","created":"2022-06-18","cited_by_count":7,"area":null},{"id":"2404.13891","title":"Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent","created":"2024-04-22","cited_by_count":7,"area":null},{"id":"2602.00528","title":"How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use","created":"2026-01-31","cited_by_count":7,"area":"lr"},{"id":"2208.10138","title":"Learning Correlated Equilibria in Mean-Field Games","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2311.00676","title":"Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2605.19928","title":"Real-Time Parallel Counterfactual Regret Minimization","created":"2026-05-19","cited_by_count":6,"area":null},{"id":"2201.10377","title":"Public Information Representation for Adversarial Team Games","created":"2022-01-25","cited_by_count":4,"area":null},{"id":"2602.16928","title":"Discovering Multiagent Learning Algorithms with Large Language Models","created":"2026-02-18","cited_by_count":4,"area":null},{"id":"2607.28520","title":"Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation","created":"2026-07-30","cited_by_count":4,"area":null},{"id":"2101.09603","title":"Optimistic and Adaptive Lagrangian Hedging","created":"2021-01-23","cited_by_count":3,"area":null},{"id":"2207.07971","title":"A Survey of Decision Making in Adversarial Games","created":"2022-07-16","cited_by_count":3,"area":null},{"id":"2310.11518","title":"Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2510.04407","title":"Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2607.14169","title":"When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models","created":"2026-07-15","cited_by_count":3,"area":"wm"},{"id":"2303.01074","title":"Learning not to Regret","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2309.00656","title":"Local and adaptive mirror descents in extensive-form games","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2402.19420","title":"Understanding Iterative Combinatorial Auction Designs via Multi-Agent Reinforcement Learning","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2510.05048","title":"Look-ahead Reasoning with a Learned Model in Imperfect Information Games","created":"2025-10-06","cited_by_count":2,"area":"lr"},{"id":"2510.17067","title":"Convergence of Regret Matching in Potential Games and Constrained Optimization","created":"2025-10-20","cited_by_count":2,"area":null},{"id":"2603.10098","title":"Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models","created":"2026-03-10","cited_by_count":2,"area":"agents"},{"id":"2605.14277","title":"Parallelizing Counterfactual Regret Minimization","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2606.28308","title":"Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2608.24731","title":"Optimal Alternating Regret for Online Learning and Games","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2306.07372","title":"Composing Efficient, Robust Tests for Policy Selection","created":"2023-06-12","cited_by_count":1,"area":null},{"id":"2401.12557","title":"Balancing the AI Strength of Roles in Self-Play Training with Regret Matching+","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2402.09456","title":"Optimistic Thompson Sampling for No-Regret Learning in Unknown Games","created":"2024-02-07","cited_by_count":1,"area":null},{"id":"2405.11746","title":"Configurable Mirror Descent: Towards a Unification of Decision Making","created":"2024-05-20","cited_by_count":1,"area":null},{"id":"2501.16600","title":"On the Power of Perturbation under Sampling in Solving Extensive-Form Games","created":"2025-01-28","cited_by_count":1,"area":null},{"id":"2503.12770","title":"Faster Game Solving via Asymmetry of Step Sizes","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2504.18868","title":"Approximating Nash Equilibria in General-Sum Games via Meta-Learning","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2508.06559","title":"Solving Pasur Using GPU-Accelerated Counterfactual Regret Minimization","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2510.15094","title":"Beyond Outcome-Based Imperfect-Recall: Higher-Resolution Abstractions for Imperfect-Information Games","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2511.08174","title":"Deep (Predictive) Discounted Counterfactual Regret Minimization","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2608.06362","title":"AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Games","created":"2026-08-06","cited_by_count":1,"area":"agents"},{"id":"2112.10890","title":"Revisiting Game Representations: The Hidden Costs of Efficiency in Sequential Decision-making Algorithms","created":"2021-12-20","cited_by_count":0,"area":null},{"id":"2205.12031","title":"Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections","created":"2022-05-24","cited_by_count":0,"area":null},{"id":"2303.11046","title":"Convergence analysis and acceleration of the smoothing methods for solving extensive-form games","created":"2023-03-20","cited_by_count":0,"area":null},{"id":"2308.11256","title":"Efficient Last-iterate Convergence Algorithms in Solving Games","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2309.03084","title":"Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2310.09658","title":"A Generalized Extensive-Form Fictitious Play Algorithm","created":"2023-10-14","cited_by_count":0,"area":null},{"id":"2402.11835","title":"Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization","created":"2024-02-19","cited_by_count":0,"area":"deeprl"},{"id":"2406.00054","title":"$\\epsilon$-Optimally Solving Zero-Sum POSGs","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2408.14778","title":"GPU-Accelerated Counterfactual Regret Minimization","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2504.18917","title":"Meta-Learning in Self-Play Regret Minimization","created":"2025-04-26","cited_by_count":0,"area":null},{"id":"2509.13653","title":"Efficient Last-Iterate Convergence in Regret Minimization via Adaptive Reward Transformation","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2509.23747","title":"Beyond Game Theory Optimal: Profit-Maximizing Poker Agents for No-Limit Holdem","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2603.06977","title":"NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2605.04979","title":"On-line Learning in Tree MDPs by Treating Policies as Bandit Arms","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.23238","title":"GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2607.00642","title":"Coachable agents for interactive gameplay","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2607.21856","title":"LeAct: Learning to Reason from Expert Actions","created":"2026-07-23","cited_by_count":0,"area":"lr"},{"id":"2607.25835","title":"Distributed Constraint Optimization via Online Learning and Iterative Pricing with Application to Large-Scale Satellite Scheduling","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.14761","title":"CFR without Unbiasedness: Deterministic Guarantees for Persistent Public-Chance Schedules","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.25182","title":"Minimax Alternating Regret for the Experts Problem and Online Convex Optimization","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.11923","title":"GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.19820","title":"Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}