{"url":"/task/board-games","name":"Board Games","slug":"board-games","description_markdown":null,"categories":[{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":131,"papers_with_code":60,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":3,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/obstacle-tower","name":"Obstacle Tower","full_name":"","num_papers_in_archive":20},{"url":"/dataset/cards-against-humanity","name":"Cards Against Humanity","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/game-of-chess","name":"Game of Chess"},{"url":"/task/game-of-go","name":"Game of Go"},{"url":"/task/game-of-shogi","name":"Game of Shogi"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":60,"tagged_in_all":131,"items":[{"url":"/paper/rlcard-a-toolkit-for-reinforcement-learning","title":"RLCard: A Toolkit for Reinforcement Learning in Card Games","date":"2019-10-10","arxiv_id":"1910.04376","repositories_listed":9,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/monte-carlo-graph-search-for-alphazero","title":"Monte-Carlo Graph Search for AlphaZero","date":"2020-12-20","arxiv_id":"2012.11045","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-play-the-chess-variant-crazyhouse","title":"Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data","date":"2019-08-19","arxiv_id":"1908.06660","repositories_listed":3,"syntology":null},{"url":"/paper/obstacle-tower-a-generalization-challenge-in","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","date":"2019-02-04","arxiv_id":"1902.01378","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/regular-boardgames","title":"Regular Boardgames","date":"2017-06-08","arxiv_id":"1706.02462","repositories_listed":3,"syntology":null},{"url":"/paper/4hammer-a-board-game-reinforcement-learning","title":"4Hammer: a board-game reinforcement learning environment for the hour long time frame","date":"2025-05-19","arxiv_id":"2505.13638","repositories_listed":2,"syntology":null},{"url":"/paper/zerosumeval-an-extensible-framework-for","title":"ZeroSumEval: An Extensible Framework For Scaling LLM Evaluation with Inter-Model Competition","date":"2025-03-10","arxiv_id":"2503.10673","repositories_listed":2,"syntology":null},{"url":"/paper/solving-royal-game-of-ur-using-reinforcement","title":"Solving Royal Game of Ur Using Reinforcement Learning","date":"2022-08-23","arxiv_id":"2208.10669","repositories_listed":2,"syntology":null},{"url":"/paper/split-moves-for-monte-carlo-tree-search","title":"Split Moves for Monte-Carlo Tree Search","date":"2021-12-14","arxiv_id":"2112.07761","repositories_listed":2,"syntology":null},{"url":"/paper/planning-in-stochastic-environments-with-a","title":"Planning in Stochastic Environments with a Learned Model","date":"2021-09-29","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/scaling-scaling-laws-with-board-games","title":"Scaling Scaling Laws with Board Games","date":"2021-04-07","arxiv_id":"2104.03113","repositories_listed":2,"syntology":{"n":20,"n_ran":0,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/improving-model-based-reinforcement-learning","title":"Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision","date":"2021-02-10","arxiv_id":"2102.05599","repositories_listed":2,"syntology":null},{"url":"/paper/explain-your-move-understanding-agent-actions-1","title":"Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution","date":"2019-12-23","arxiv_id":"1912.12191","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/a0c-alpha-zero-in-continuous-action-space","title":"A0C: Alpha Zero in Continuous Action Space","date":"2018-05-24","arxiv_id":"1805.09613","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/monte-carlo-q-learning-for-general-game","title":"Monte Carlo Q-learning for General Game Playing","date":"2018-02-16","arxiv_id":"1802.05944","repositories_listed":2,"syntology":null},{"url":"/paper/adaptive-action-duration-with-contextual","title":"Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments","date":"2025-06-17","arxiv_id":"2507.00030","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-models-are-biased","title":"Vision Language Models are Biased","date":"2025-05-29","arxiv_id":"2505.23941","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/playing-non-embedded-card-based-games-with","title":"Playing Non-Embedded Card-Based Games with Reinforcement Learning","date":"2025-04-07","arxiv_id":"2504.04783","repositories_listed":1,"syntology":null},{"url":"/paper/playing-hex-and-counter-wargames-using","title":"Playing Hex and Counter Wargames using Reinforcement Learning and Recurrent Neural Networks","date":"2025-02-19","arxiv_id":"2502.13918","repositories_listed":1,"syntology":null},{"url":"/paper/alphazero-neural-scaling-and-zipf-s-law-a","title":"AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws","date":"2024-12-16","arxiv_id":"2412.11979","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/flexible-game-playing-ai-with-alphavit","title":"AlphaViT: A Flexible Game-Playing AI for Multiple Games and Variable Board Sizes","date":"2024-08-25","arxiv_id":"2408.13871","repositories_listed":1,"syntology":null},{"url":"/paper/perceptual-similarity-for-measuring-decision","title":"Perceptual Similarity for Measuring Decision-Making Style and Policy Diversity in Games","date":"2024-08-12","arxiv_id":"2408.06051","repositories_listed":1,"syntology":null},{"url":"/paper/gavel-generating-games-via-evolution-and","title":"GAVEL: Generating Games Via Evolution and Language Models","date":"2024-07-12","arxiv_id":"2407.09388","repositories_listed":1,"syntology":null},{"url":"/paper/robocupgym-a-challenging-continuous-control","title":"RobocupGym: A challenging continuous control benchmark in Robocup","date":"2024-07-03","arxiv_id":"2407.14516","repositories_listed":1,"syntology":null},{"url":"/paper/robust-model-based-reinforcement-learning-1","title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","date":"2024-06-14","arxiv_id":"2406.09976","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/injecting-combinatorial-optimization-into","title":"Injecting Combinatorial Optimization into MCTS: Application to the Board Game boop","date":"2024-06-13","arxiv_id":"2406.08766","repositories_listed":1,"syntology":null},{"url":"/paper/rezero-boosting-mcts-based-algorithms-by-just","title":"ReZero: Boosting MCTS-based Algorithms by Backward-view and Entire-buffer Reanalyze","date":"2024-04-25","arxiv_id":"2404.16364","repositories_listed":1,"syntology":null},{"url":"/paper/playing-board-games-with-the-predict-results","title":"Playing Board Games with the Predict Results of Beam Search Algorithm","date":"2024-04-23","arxiv_id":"2404.16072","repositories_listed":1,"syntology":null},{"url":"/paper/archiguesser-ai-art-architecture-educational","title":"ArchiGuesser -- AI Art Architecture Educational Game","date":"2023-12-14","arxiv_id":"2312.09334","repositories_listed":1,"syntology":null},{"url":"/paper/from-images-to-connections-can-dqn-with-gnns","title":"From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex?","date":"2023-11-22","arxiv_id":"2311.13414","repositories_listed":1,"syntology":null}],"syntology_records":8,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}