{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":131,"of_with_code":60,"tagged_in_all":131,"counts":{"archive_papers_tagged":131,"with_a_code_link":60,"where_syntology_ran_a_sample":12,"not_listed_spam_title":0,"listed":131,"listed_where_code_ran":12,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/rlcard-a-toolkit-for-reinforcement-learning","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rlcard-a-toolkit-for-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1910.04376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04376"}},"official":{"repos":["datamllab/rlcard"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/monte-carlo-graph-search-for-alphazero","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/obstacle-tower-a-generalization-challenge-in#ran","syntology_url":"https://syntology.ai/paper/1902.01378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01378"}},"official":{"repos":["Unity-Technologies/obstacle-tower-env"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/regular-boardgames","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/scaling-scaling-laws-with-board-games#ran","syntology_url":"https://syntology.ai/paper/2104.03113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03113"}},"official":null}},{"url":"/paper/improving-model-based-reinforcement-learning","slug":"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","slug":"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_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/explain-your-move-understanding-agent-actions-1#ran","syntology_url":"https://syntology.ai/paper/1912.12191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.12191"}},"official":{"repos":["rl-interpretation/understandingRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/a0c-alpha-zero-in-continuous-action-space","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a0c-alpha-zero-in-continuous-action-space#ran","syntology_url":"https://syntology.ai/paper/1805.09613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09613"}},"official":null}},{"url":"/paper/monte-carlo-q-learning-for-general-game","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vision-language-models-are-biased#ran","syntology_url":"https://syntology.ai/paper/2505.23941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23941"}},"official":{"repos":["anvo25/vlms-are-biased"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/playing-non-embedded-card-based-games-with","slug":"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","slug":"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","slug":"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":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/alphazero-neural-scaling-and-zipf-s-law-a#ran","syntology_url":"https://syntology.ai/paper/2412.11979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11979"}},"official":{"repos":["orenneumann/alphazero_zipfs_law"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flexible-game-playing-ai-with-alphavit","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robust-model-based-reinforcement-learning-1#ran","syntology_url":"https://syntology.ai/paper/2406.09976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09976"}},"official":{"repos":["rmbpo-eval/rmbpo-eval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/injecting-combinatorial-optimization-into","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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},{"url":"/paper/game-solving-with-online-fine-tuning","slug":"game-solving-with-online-fine-tuning","title":"Game Solving with Online Fine-Tuning","date":"2023-11-13","arxiv_id":"2311.07178","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/game-solving-with-online-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2311.07178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07178"}},"official":{"repos":["rlglab/online-fine-tuning-solver"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hybrid-minimax-mcts-and-difficulty-adjustment","slug":"hybrid-minimax-mcts-and-difficulty-adjustment","title":"Hybrid Minimax-MCTS and Difficulty Adjustment for General Game Playing","date":"2023-10-25","arxiv_id":"2310.16581","repositories_listed":1,"syntology":null},{"url":"/paper/minizero-comparative-analysis-of-alphazero","slug":"minizero-comparative-analysis-of-alphazero","title":"MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games","date":"2023-10-17","arxiv_id":"2310.11305","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/minizero-comparative-analysis-of-alphazero#ran","syntology_url":"https://syntology.ai/paper/2310.11305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11305"}},"official":{"repos":["rlglab/minizero"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lightzero-a-unified-benchmark-for-monte-carlo-1","slug":"lightzero-a-unified-benchmark-for-monte-carlo-1","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","date":"2023-10-12","arxiv_id":"2310.08348","repositories_listed":1,"syntology":null},{"url":"/paper/machine-learning-powered-pricing-of-the","slug":"machine-learning-powered-pricing-of-the","title":"Machine Learning-powered Pricing of the Multidimensional Passport Option","date":"2023-07-27","arxiv_id":"2307.14887","repositories_listed":1,"syntology":null},{"url":"/paper/pytag-challenges-and-opportunities-for","slug":"pytag-challenges-and-opportunities-for","title":"PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games","date":"2023-07-19","arxiv_id":"2307.09905","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-beyond-task-performance-analyzing","slug":"evaluation-beyond-task-performance-analyzing","title":"Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex","date":"2022-11-26","arxiv_id":"2211.14673","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluation-beyond-task-performance-analyzing#ran","syntology_url":"https://syntology.ai/paper/2211.14673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.14673"}},"official":{"repos":["jzf2101/alphatology"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/are-alphazero-like-agents-robust-to","slug":"are-alphazero-like-agents-robust-to","title":"Are AlphaZero-like Agents Robust to Adversarial Perturbations?","date":"2022-11-07","arxiv_id":"2211.03769","repositories_listed":1,"syntology":null},{"url":"/paper/mastering-the-game-of-stratego-with-model","slug":"mastering-the-game-of-stratego-with-model","title":"Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning","date":"2022-06-30","arxiv_id":"2206.15378","repositories_listed":1,"syntology":null},{"url":"/paper/impartial-games-a-challenge-for-reinforcement","slug":"impartial-games-a-challenge-for-reinforcement","title":"Impartial Games: A Challenge for Reinforcement Learning","date":"2022-05-25","arxiv_id":"2205.12787","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-approach-to-solving-goal-achieving","slug":"a-novel-approach-to-solving-goal-achieving","title":"A Novel Approach to Solving Goal-Achieving Problems for Board Games","date":"2021-12-05","arxiv_id":"2112.02563","repositories_listed":1,"syntology":null},{"url":"/paper/alphadda-game-artificial-intelligence-with","slug":"alphadda-game-artificial-intelligence-with","title":"AlphaDDA: Strategies for Adjusting the Playing Strength of a Fully Trained AlphaZero System to a Suitable Human Training Partner","date":"2021-11-11","arxiv_id":"2111.06266","repositories_listed":1,"syntology":null},{"url":"/paper/alphazero-based-proof-cost-network-to-aid","slug":"alphazero-based-proof-cost-network-to-aid","title":"AlphaZero-based Proof Cost Network to Aid Game Solving","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/estimates-for-the-branching-factors-of-atari","slug":"estimates-for-the-branching-factors-of-atari","title":"Estimates for the Branching Factors of Atari Games","date":"2021-07-06","arxiv_id":"2107.02385","repositories_listed":1,"syntology":null},{"url":"/paper/playing-codenames-with-language-graphs-and","slug":"playing-codenames-with-language-graphs-and","title":"Playing Codenames with Language Graphs and Word Embeddings","date":"2021-05-12","arxiv_id":"2105.05885","repositories_listed":1,"syntology":null},{"url":"/paper/playing-against-the-board-rolling-horizon","slug":"playing-against-the-board-rolling-horizon","title":"Playing Against the Board: Rolling Horizon Evolutionary Algorithms Against Pandemic","date":"2021-03-28","arxiv_id":"2103.15090","repositories_listed":1,"syntology":null},{"url":"/paper/mastering-terra-mystica-applying-self-play-to","slug":"mastering-terra-mystica-applying-self-play-to","title":"Mastering Terra Mystica: Applying Self-Play to Multi-agent Cooperative Board Games","date":"2021-02-21","arxiv_id":"2102.10540","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-general-game-playing-with","slug":"deep-learning-for-general-game-playing-with","title":"Deep Learning for General Game Playing with Ludii and Polygames","date":"2021-01-23","arxiv_id":"2101.09562","repositories_listed":1,"syntology":null},{"url":"/paper/design-and-implementation-of-tag-a-tabletop","slug":"design-and-implementation-of-tag-a-tabletop","title":"Design and Implementation of TAG: A Tabletop Games Framework","date":"2020-09-25","arxiv_id":"2009.12065","repositories_listed":1,"syntology":null},{"url":"/paper/manipulating-the-distributions-of-experience","slug":"manipulating-the-distributions-of-experience","title":"Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration","date":"2020-05-30","arxiv_id":"2006.00283","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning","slug":"reinforcement-learning","title":"Reinforcement Learning","date":"2020-05-29","arxiv_id":"2005.14419","repositories_listed":1,"syntology":null},{"url":"/paper/explain-your-move-understanding-agent-actions","slug":"explain-your-move-understanding-agent-actions","title":"Explain Your Move: Understanding Agent Actions Using Focused Feature Saliency","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/nmbr9-as-a-constraint-programming-challenge","slug":"nmbr9-as-a-constraint-programming-challenge","title":"Nmbr9 as a Constraint Programming Challenge","date":"2020-01-13","arxiv_id":"2001.04238","repositories_listed":1,"syntology":null},{"url":"/paper/state-representation-and-polyomino-placement","slug":"state-representation-and-polyomino-placement","title":"State Representation and Polyomino Placement for the Game Patchwork","date":"2020-01-13","arxiv_id":"2001.04233","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-language-games-for-advanced","slug":"adversarial-language-games-for-advanced","title":"Adversarial Language Games for Advanced Natural Language Intelligence","date":"2019-11-05","arxiv_id":"1911.01622","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-language-games-for-advanced#ran","syntology_url":"https://syntology.ai/paper/1911.01622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.01622"}},"official":null}},{"url":"/paper/biasing-mcts-with-features-for-general-games","slug":"biasing-mcts-with-features-for-general-games","title":"Biasing MCTS with Features for General Games","date":"2019-03-21","arxiv_id":"1903.08942","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-the-potential-of-classical-q","slug":"assessing-the-potential-of-classical-q","title":"Assessing the Potential of Classical Q-learning in General Game Playing","date":"2018-10-14","arxiv_id":"1810.06078","repositories_listed":1,"syntology":null},{"url":"/paper/the-text-based-adventure-ai-competition","slug":"the-text-based-adventure-ai-competition","title":"The Text-Based Adventure AI Competition","date":"2018-08-03","arxiv_id":"1808.01262","repositories_listed":1,"syntology":null},{"url":"/paper/beating-the-worlds-best-at-super-smash-bros","slug":"beating-the-worlds-best-at-super-smash-bros","title":"Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning","date":"2017-02-21","arxiv_id":"1702.06230","repositories_listed":1,"syntology":null},{"url":"/paper/move-evaluation-in-go-using-deep","slug":"move-evaluation-in-go-using-deep","title":"Move Evaluation in Go Using Deep Convolutional Neural Networks","date":"2014-12-20","arxiv_id":"1412.6564","repositories_listed":1,"syntology":null},{"url":null,"slug":"xiangqi-r1-enhancing-spatial-strategic","title":"Xiangqi-R1: Enhancing Spatial Strategic Reasoning in LLMs for Chinese Chess via Reinforcement Learning","date":"2025-07-16","arxiv_id":"2507.12215","repositories_listed":0,"syntology":null},{"url":null,"slug":"spin-bench-how-well-do-llms-plan","title":"SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?","date":"2025-03-16","arxiv_id":"2503.12349","repositories_listed":0,"syntology":null},{"url":null,"slug":"rotated-bitboards-in-fusc-and-reinforcement","title":"Reinforcement Learning and Life Cycle Assessment for a Circular Economy -- Towards Progressive Computer Science","date":"2025-03-13","arxiv_id":"2503.10822","repositories_listed":0,"syntology":null},{"url":null,"slug":"python-agent-in-ludii","title":"Python Agent in Ludii","date":"2024-12-18","arxiv_id":"2412.14372","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastering-board-games-by-external-and","title":"Mastering Board Games by External and Internal Planning with Language Models","date":"2024-12-02","arxiv_id":"2412.12119","repositories_listed":0,"syntology":null},{"url":null,"slug":"anytime-sequential-halving-in-monte-carlo","title":"Anytime Sequential Halving in Monte-Carlo Tree Search","date":"2024-11-11","arxiv_id":"2411.07171","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpreting-the-learned-model-in-muzero","title":"Interpreting the Learned Model in MuZero Planning","date":"2024-11-07","arxiv_id":"2411.04580","repositories_listed":0,"syntology":null},{"url":null,"slug":"restnet-defense-against-adversarial-policies","title":"ResTNet: Defense against Adversarial Policies via Transformer in Computer Go","date":"2024-10-07","arxiv_id":"2410.05347","repositories_listed":0,"syntology":null},{"url":null,"slug":"people-use-fast-goal-directed-simulation-to","title":"People use fast, goal-directed simulation to reason about novel games","date":"2024-07-19","arxiv_id":"2407.14095","repositories_listed":0,"syntology":null},{"url":null,"slug":"games-of-knightian-uncertainty","title":"Games of Knightian Uncertainty as AGI testbeds","date":"2024-06-26","arxiv_id":"2406.18178","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-play-7-wonders-duel-without-human","title":"Learning to Play 7 Wonders Duel Without Human Supervision","date":"2024-06-02","arxiv_id":"2406.00741","repositories_listed":0,"syntology":null},{"url":null,"slug":"extreme-value-monte-carlo-tree-search","title":"Extreme Value Monte Carlo Tree Search","date":"2024-05-28","arxiv_id":"2405.18248","repositories_listed":0,"syntology":null},{"url":null,"slug":"demand-response-for-residential-building","title":"Demand response for residential building heating: Effective Monte Carlo Tree Search control based on physics-informed neural networks","date":"2023-12-06","arxiv_id":"2312.03365","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-tabletop-game-design-a-case","title":"Evolutionary Tabletop Game Design: A Case Study in the Risk Game","date":"2023-10-30","arxiv_id":"2310.20008","repositories_listed":0,"syntology":null},{"url":null,"slug":"alphazero-gomoku","title":"AlphaZero Gomoku","date":"2023-09-04","arxiv_id":"2309.01294","repositories_listed":0,"syntology":null},{"url":null,"slug":"developmental-bootstrapping-of-ais","title":"Bootstrapping Developmental AIs: From Simple Competences to Intelligent Human-Compatible AIs","date":"2023-08-08","arxiv_id":"2308.04586","repositories_listed":0,"syntology":null},{"url":null,"slug":"stimulating-student-engagement-with-an-ai","title":"Stimulating student engagement with an AI board game tournament","date":"2023-04-22","arxiv_id":"2304.11376","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-reinforcement-learning-a-survey","title":"Evolutionary Reinforcement Learning: A Survey","date":"2023-03-07","arxiv_id":"2303.04150","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-concise-logical-patterns-by","title":"Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size","date":"2023-01-19","arxiv_id":"2301.08190","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-board-game-distance","title":"Measuring Board Game Distance","date":"2023-01-10","arxiv_id":"2301.03913","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalised-agent-for-solving-higher-board","title":"Generalised agent for solving higher board states of tic tac toe using Reinforcement Learning","date":"2022-12-23","arxiv_id":"2212.12252","repositories_listed":0,"syntology":null},{"url":null,"slug":"teacher-student-curriculum-learning-for","title":"Teacher-student curriculum learning for reinforcement learning","date":"2022-10-31","arxiv_id":"2210.17368","repositories_listed":0,"syntology":null},{"url":null,"slug":"spending-thinking-time-wisely-accelerating-1","title":"Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions","date":"2022-10-23","arxiv_id":"2210.12628","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-adaptive-mcts-with-td-learning-in","title":"Exploring Adaptive MCTS with TD Learning in miniXCOM","date":"2022-10-10","arxiv_id":"2210.05014","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-technique-to-create-weaker-abstract-board","title":"A Technique to Create Weaker Abstract Board Game Agents via Reinforcement Learning","date":"2022-09-01","arxiv_id":"2209.00711","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-cost-of-passing-using-deep-learning-ais","title":"The cost of passing -- using deep learning AIs to expand our understanding of the ancient game of Go","date":"2022-08-24","arxiv_id":"2208.12643","repositories_listed":0,"syntology":null},{"url":null,"slug":"runtime-analysis-of-competitive-co","title":"Runtime Analysis of Competitive co-Evolutionary Algorithms for Maximin Optimisation of a Bilinear Function","date":"2022-06-30","arxiv_id":"2206.15238","repositories_listed":0,"syntology":null},{"url":null,"slug":"pgd-a-large-scale-professional-go-dataset-for","title":"PGD: A Large-scale Professional Go Dataset for Data-driven Analytics","date":"2022-04-30","arxiv_id":"2205.00254","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-23-mw-data-centre-is-all-you-need","title":"A 23 MW data centre is all you need","date":"2022-03-31","arxiv_id":"2203.17265","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-state-action-features-for-general","title":"Spatial State-Action Features for General Games","date":"2022-01-17","arxiv_id":"2201.06401","repositories_listed":0,"syntology":null},{"url":null,"slug":"final-adaptation-reinforcement-learning-for-n","title":"Final Adaptation Reinforcement Learning for N-Player Games","date":"2021-11-29","arxiv_id":"2111.14375","repositories_listed":0,"syntology":null},{"url":null,"slug":"gapoera-application-programming-interface-for","title":"Gapoera: Application Programming Interface for AI Environment of Indonesian Board Game","date":"2021-10-22","arxiv_id":"2110.11924","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-generation-of-board-game-manuals","title":"Automatic Generation of Board Game Manuals","date":"2021-09-20","arxiv_id":"2109.09507","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-level-reinforcement-learning-through","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","date":"2021-07-27","arxiv_id":"2107.12544","repositories_listed":0,"syntology":null},{"url":null,"slug":"train-on-small-play-the-large-scaling-up","title":"Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN","date":"2021-07-18","arxiv_id":"2107.08387","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-board-game-concepts","title":"General Board Game Concepts","date":"2021-07-02","arxiv_id":"2107.01078","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-warm-start-mcts-in-alphazero-like","title":"Adaptive Warm-Start MCTS in AlphaZero-like Deep Reinforcement Learning","date":"2021-05-13","arxiv_id":"2105.06136","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-power-of-refined-skat-selection","title":"On the Power of Refined Skat Selection","date":"2021-04-07","arxiv_id":"2104.02997","repositories_listed":0,"syntology":null},{"url":null,"slug":"collaborative-agent-gameplay-in-the-pandemic","title":"Collaborative Agent Gameplay in the Pandemic Board Game","date":"2021-03-21","arxiv_id":"2103.11388","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-off-and-on-policy-training-in-model","title":"Combining Off and On-Policy Training in Model-Based Reinforcement Learning","date":"2021-02-24","arxiv_id":"2102.12194","repositories_listed":0,"syntology":null}],"syntology_records":12,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":12,"papers_where_code_ran_first_page":"/task/board-games/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/board-games/papers/2","json":"/task/board-games/papers/2.json","rows":31},{"order":"ran","page":1,"of":1,"url":"/task/board-games/papers/ran/1","json":"/task/board-games/papers/ran/1.json","rows":12}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"d2e279500a7b5d4f6560a3e6373a148bddbb961d56514278f14712511eeb3ced","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}