{"total":20,"rows":[{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"area":null},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"area":null},{"id":"2107.01825","title":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation","created":"2021-07-05","cited_by_count":18,"area":null},{"id":"2203.16406","title":"PerfectDou: Dominating DouDizhu with Perfect Information Distillation","created":"2022-03-30","cited_by_count":15,"area":null},{"id":"2410.06195","title":"EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"id":"2406.16382","title":"UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2112.12845","title":"Automatic Meta-Path Discovery for Effective Graph-Based Recommendation","created":"2021-12-23","cited_by_count":5,"area":null},{"id":"2509.01328","title":"Can Large Language Models Master Complex Card Games?","created":"2025-09-01","cited_by_count":4,"area":null},{"id":"2502.07128","title":"Cardiverse: Harnessing LLMs for Novel Card Game Prototyping","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2405.18123","title":"PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2302.14329","title":"Towards Personalized Preprocessing Pipeline Search","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2307.09905","title":"PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games","created":"2023-07-19","cited_by_count":1,"area":null},{"id":"2509.04125","title":"Analysis of Bluffing by DQN and CFR in Leduc Hold'em Poker","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2110.10374","title":"Playing 2048 With Reinforcement Learning","created":"2021-10-20","cited_by_count":0,"area":null},{"id":"2209.05466","title":"Hearts Gym: Learning Reinforcement Learning as a Team Event","created":"2022-09-07","cited_by_count":0,"area":null},{"id":"2311.17305","title":"Two-Step Reinforcement Learning for Multistage Strategy Card Game","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2407.10279","title":"AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding","created":"2024-07-14","cited_by_count":0,"area":null},{"id":"2512.19210","title":"Observer, Not Player: Simulating Theory of Mind in LLMs through Game Observation","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2603.03252","title":"Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games","created":"2026-03-03","cited_by_count":0,"area":null}],"next_cursor":null}