{"total":22,"rows":[{"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":"2210.12530","title":"LMPriors: Pre-Trained Language Models as Task-Specific Priors","created":"2022-10-22","cited_by_count":56,"area":null},{"id":"2210.05492","title":"Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning","created":"2022-10-11","cited_by_count":48,"area":null},{"id":"2310.08901","title":"Welfare Diplomacy: Benchmarking Language Model Cooperation","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2303.08721","title":"Artificial Influence: An Analysis Of AI-Driven Persuasion","created":"2023-03-15","cited_by_count":33,"area":null},{"id":"2112.03178","title":"Student of Games: A unified learning algorithm for both perfect and imperfect information games","created":"2021-12-06","cited_by_count":23,"area":null},{"id":"2205.15294","title":"Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent","created":"2022-05-30","cited_by_count":15,"area":null},{"id":"2306.10225","title":"Genes in Intelligent Agents","created":"2023-06-17","cited_by_count":9,"area":null},{"id":"2406.04643","title":"More Victories, Less Cooperation: Assessing Cicero's Diplomacy Play","created":"2024-06-07","cited_by_count":9,"area":null},{"id":"2311.08666","title":"It Takes Two to Negotiate: Modeling Social Exchange in Online Multiplayer Games","created":"2023-11-15","cited_by_count":8,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2407.15255","title":"Explaining Decisions of Agents in Mixed-Motive Games","created":"2024-07-21","cited_by_count":4,"area":null},{"id":"2506.09655","title":"DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2207.08894","title":"A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games","created":"2022-07-18","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":"2411.09109","title":"Personalized Help for Optimizing Low-Skilled Users' Strategy","created":"2024-11-14","cited_by_count":3,"area":null},{"id":"2502.12436","title":"Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2502.16339","title":"Dynamic Coalition Structure Detection in Natural Language-based Interactions","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2209.10958","title":"Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments","created":"2022-09-22","cited_by_count":2,"area":null},{"id":"2211.12615","title":"AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies","created":"2022-11-22","cited_by_count":2,"area":null},{"id":"2212.14104","title":"Towards automating Codenames spymasters with deep reinforcement learning","created":"2022-12-28","cited_by_count":1,"area":null},{"id":"2212.14431","title":"Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information Games","created":"2022-12-29","cited_by_count":1,"area":null}],"next_cursor":null}