{"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/card-games","name":"Card Games","slug":"card-games","description_markdown":"Card games involve playing cards: the task is to train an agent to play the game with specified rules and beat other players.","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":52,"papers_with_code":23,"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":1,"subtasks":4,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/cards-against-humanity","name":"Cards Against Humanity","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/game-of-hanabi","name":"Game of Hanabi"},{"url":"/task/game-of-poker","name":"Game of Poker"},{"url":"/task/klondike","name":"Klondike"},{"url":"/task/solitaire","name":"Solitaire"}],"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":1,"rows_per_page":100,"shown":52,"of":52,"of_with_code":23,"tagged_in_all":52,"counts":{"archive_papers_tagged":52,"with_a_code_link":23,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":52,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/deep-reinforcement-learning-from-self-play-in","slug":"deep-reinforcement-learning-from-self-play-in","title":"Deep Reinforcement Learning from Self-Play in Imperfect-Information Games","date":"2016-03-03","arxiv_id":"1603.01121","repositories_listed":7,"syntology":null},{"url":"/paper/gtbench-uncovering-the-strategic-reasoning","slug":"gtbench-uncovering-the-strategic-reasoning","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","date":"2024-02-19","arxiv_id":"2402.12348","repositories_listed":2,"syntology":null},{"url":"/paper/survey-of-artificial-intelligence-for-card","slug":"survey-of-artificial-intelligence-for-card","title":"Survey of Artificial Intelligence for Card Games and Its Application to the Swiss Game Jass","date":"2019-06-11","arxiv_id":"1906.04439","repositories_listed":2,"syntology":null},{"url":"/paper/application-of-self-play-reinforcement","slug":"application-of-self-play-reinforcement","title":"Application of Self-Play Reinforcement Learning to a Four-Player Game of Imperfect Information","date":"2018-08-30","arxiv_id":"1808.10442","repositories_listed":2,"syntology":null},{"url":"/paper/latent-predictor-networks-for-code-generation","slug":"latent-predictor-networks-for-code-generation","title":"Latent Predictor Networks for Code Generation","date":"2016-03-22","arxiv_id":"1603.06744","repositories_listed":2,"syntology":null},{"url":"/paper/optimizing-hearthstone-agents-using-an","slug":"optimizing-hearthstone-agents-using-an","title":"Optimizing Hearthstone Agents using an Evolutionary Algorithm","date":"2024-10-25","arxiv_id":"2410.19681","repositories_listed":1,"syntology":null},{"url":"/paper/identifying-and-clustering-counter","slug":"identifying-and-clustering-counter","title":"Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Balance Analysis","date":"2024-08-30","arxiv_id":"2408.17180","repositories_listed":1,"syntology":null},{"url":"/paper/alphadou-high-performance-end-to-end-doudizhu","slug":"alphadou-high-performance-end-to-end-doudizhu","title":"AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding","date":"2024-07-14","arxiv_id":"2407.10279","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-commentary-strategies-for-imperfect","slug":"enhancing-commentary-strategies-for-imperfect","title":"Enhancing Commentary Strategies for Imperfect Information Card Games: A Study of Large Language Models in Guandan Commentary","date":"2024-06-23","arxiv_id":"2406.17807","repositories_listed":1,"syntology":null},{"url":"/paper/danzero-dominating-the-guandan-game-through","slug":"danzero-dominating-the-guandan-game-through","title":"DanZero+: Dominating the GuanDan Game through Reinforcement Learning","date":"2023-12-05","arxiv_id":"2312.02561","repositories_listed":1,"syntology":null},{"url":"/paper/suspicion-agent-playing-imperfect-information","slug":"suspicion-agent-playing-imperfect-information","title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","date":"2023-09-29","arxiv_id":"2309.17277","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/suspicion-agent-playing-imperfect-information#ran","syntology_url":"https://syntology.ai/paper/2309.17277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17277"}},"official":{"repos":["cr-gjx/suspicion-agent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/introducing-tales-of-tribute-ai-competition","slug":"introducing-tales-of-tribute-ai-competition","title":"Introducing Tales of Tribute AI Competition","date":"2023-05-14","arxiv_id":"2305.08234","repositories_listed":1,"syntology":null},{"url":"/paper/towards-computationally-efficient","slug":"towards-computationally-efficient","title":"Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs","date":"2023-02-24","arxiv_id":"2302.12676","repositories_listed":1,"syntology":null},{"url":"/paper/douzero-mastering-doudizhu-with-self-play","slug":"douzero-mastering-doudizhu-with-self-play","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","date":"2021-06-11","arxiv_id":"2106.06135","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/douzero-mastering-doudizhu-with-self-play#ran","syntology_url":"https://syntology.ai/paper/2106.06135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06135"}},"official":{"repos":["kwai/DouZero"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/predicting-human-card-selection-in-magic-the","slug":"predicting-human-card-selection-in-magic-the","title":"Predicting Human Card Selection in Magic: The Gathering with Contextual Preference Ranking","date":"2021-05-25","arxiv_id":"2105.11864","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-of-evolutionary-program-synthesis","slug":"analysis-of-evolutionary-program-synthesis","title":"Analysis of Evolutionary Program Synthesis for Card Games","date":"2021-01-08","arxiv_id":"2101.03172","repositories_listed":1,"syntology":null},{"url":"/paper/drafting-in-collectible-card-games-via","slug":"drafting-in-collectible-card-games-via","title":"Drafting in Collectible Card Games via Reinforcement Learning","date":"2020-11-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-winnability-of-klondike-and-many-other","slug":"the-winnability-of-klondike-and-many-other","title":"The Winnability of Klondike Solitaire and Many Other Patience Games","date":"2019-06-28","arxiv_id":"1906.12314","repositories_listed":1,"syntology":null},{"url":"/paper/combinational-q-learning-for-dou-di-zhu","slug":"combinational-q-learning-for-dou-di-zhu","title":"Combinational Q-Learning for Dou Di Zhu","date":"2019-01-24","arxiv_id":"1901.08925","repositories_listed":1,"syntology":null},{"url":"/paper/approximating-poker-probabilities-with-deep","slug":"approximating-poker-probabilities-with-deep","title":"Approximating Poker Probabilities with Deep Learning","date":"2018-08-22","arxiv_id":"1808.07220","repositories_listed":1,"syntology":null},{"url":"/paper/q-deckrec-a-fast-deck-recommendation-system","slug":"q-deckrec-a-fast-deck-recommendation-system","title":"Q-DeckRec: A Fast Deck Recommendation System for Collectible Card Games","date":"2018-06-26","arxiv_id":"1806.09771","repositories_listed":1,"syntology":null},{"url":null,"slug":"reinforcement-learning-for-hanabi","title":"Reinforcement Learning for Hanabi","date":"2025-05-31","arxiv_id":"2506.00458","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":"gtr-guided-thought-reinforcement-prevents","title":"GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training","date":"2025-03-11","arxiv_id":"2503.08525","repositories_listed":0,"syntology":null},{"url":null,"slug":"gflowvlm-enhancing-multi-step-reasoning-in","title":"GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks","date":"2025-03-09","arxiv_id":"2503.06514","repositories_listed":0,"syntology":null},{"url":null,"slug":"cardiverse-harnessing-llms-for-novel-card","title":"Cardiverse: Harnessing LLMs for Novel Card Game Prototyping","date":"2025-02-10","arxiv_id":"2502.07128","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-taxonomy-of-collectible-card-games-from-a","title":"A Taxonomy of Collectible Card Games from a Game-Playing AI Perspective","date":"2024-10-08","arxiv_id":"2410.06299","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-of-preferences-with-a","title":"Contrastive Learning of Preferences with a Contextual InfoNCE Loss","date":"2024-07-08","arxiv_id":"2407.05898","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-with-generalised-card","title":"Learning With Generalised Card Representations for \"Magic: The Gathering\"","date":"2024-07-08","arxiv_id":"2407.05879","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-beat-byterl-exploitability-of","title":"Learning to Beat ByteRL: Exploitability of Collectible Card Game Agents","date":"2024-04-25","arxiv_id":"2404.16689","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-planning-in-the-observation","title":"Transformer Based Planning in the Observation Space with Applications to Trick Taking Card Games","date":"2024-04-19","arxiv_id":"2404.13150","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-step-reinforcement-learning-for","title":"Two-Step Reinforcement Learning for Multistage Strategy Card Game","date":"2023-11-29","arxiv_id":"2311.17305","repositories_listed":0,"syntology":null},{"url":null,"slug":"history-filtering-in-imperfect-information","title":"History Filtering in Imperfect Information Games: Algorithms and Complexity","date":"2023-11-24","arxiv_id":"2311.14651","repositories_listed":0,"syntology":null},{"url":null,"slug":"danzero-mastering-guandan-game-with","title":"DanZero: Mastering GuanDan Game with Reinforcement Learning","date":"2022-10-31","arxiv_id":"2210.17087","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-modern-card-games-with-large-scale","title":"Towards Modern Card Games with Large-Scale Action Spaces Through Action Representation","date":"2022-06-25","arxiv_id":"2206.12700","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-complexity-of-dark-chinese-chess","title":"On the complexity of Dark Chinese Chess","date":"2021-12-06","arxiv_id":"2112.02989","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolving-evaluation-functions-for-collectible","title":"Evolving Evaluation Functions for Collectible Card Game AI","date":"2021-05-03","arxiv_id":"2105.01115","repositories_listed":0,"syntology":null},{"url":null,"slug":"elo-system-for-skat-and-other-games-of-chance","title":"ELO System for Skat and Other Games of Chance","date":"2021-04-07","arxiv_id":"2104.05422","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-based-paranoia-search-in-trick","title":"Knowledge-Based Paranoia Search in Trick-Taking","date":"2021-04-07","arxiv_id":"2104.05423","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-approach-to-collectible-card","title":"Evolutionary Approach to Collectible Card Game Arena Deckbuilding using Active Genes","date":"2020-01-05","arxiv_id":"2001.01326","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-many-ai-challenges-of-hearthstone","title":"The Many AI Challenges of Hearthstone","date":"2019-07-15","arxiv_id":"1907.06562","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-policies-from-human-data-for-skat","title":"Learning Policies from Human Data for Skat","date":"2019-05-27","arxiv_id":"1905.10907","repositories_listed":0,"syntology":null},{"url":null,"slug":"policy-based-inference-in-trick-taking-card","title":"Policy Based Inference in Trick-Taking Card Games","date":"2019-05-27","arxiv_id":"1905.10911","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-the-hearthstone-ai-competition","title":"Introducing the Hearthstone-AI Competition","date":"2019-05-06","arxiv_id":"1906.04238","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-search-with-supervised-learning-in","title":"Improving Search with Supervised Learning in Trick-Based Card Games","date":"2019-03-22","arxiv_id":"1903.09604","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-networks-models-for-analyzing-magic","title":"Neural Networks Models for Analyzing Magic: the Gathering Cards","date":"2018-10-08","arxiv_id":"1810.03744","repositories_listed":0,"syntology":null},{"url":null,"slug":"aggregated-semantic-matching-for-short-text","title":"Aggregated Semantic Matching for Short Text Entity Linking","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"procedural-content-generation-via-machine","title":"Procedural Content Generation via Machine Learning (PCGML)","date":"2017-02-02","arxiv_id":"1702.00539","repositories_listed":0,"syntology":null},{"url":null,"slug":"poker-cnn-a-pattern-learning-strategy-for","title":"Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games","date":"2015-09-22","arxiv_id":"1509.06731","repositories_listed":0,"syntology":null},{"url":null,"slug":"riffled-independence-for-ranked-data","title":"Riffled Independence for Ranked Data","date":"2009-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":3,"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":3,"papers_where_code_ran_first_page":"/task/card-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":"ran","page":1,"of":1,"url":"/task/card-games/papers/ran/1","json":"/task/card-games/papers/ran/1.json","rows":3}],"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":"7c6cbb6d641c618c437d770ef3c9c45fbb9b7faf19e3240325922beaa9d754aa","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}