{"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":"/method/douzero","slug":"douzero","name":"DouZero","full_name":"DouZero","full_name_withheld":false,"description_markdown":"**DouZero** is an AI system for the card game DouDizhu that enhances traditional Monte-Carlo methods with deep neural networks, action encoding, and parallel actors. The [Q-network](https://paperswithcode.com/method/dqn) of DouZero consists of an [LSTM](https://paperswithcode.com/method/lstm) to encode historical actions and six layers of [MLP](https://paperswithcode.com/method/feedforward-network) with hidden dimension of 512. The network predicts a value for a given state-action pair based on the concatenated representation of action and state.","description_state":"present","introduced_year":null,"introduced_by":{"title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","paper":"/paper/douzero-mastering-doudizhu-with-self-play","first_author":"Daochen Zha","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/douzero-mastering-doudizhu-with-self-play"},"source":{"url":"https://arxiv.org/abs/2106.06135v1","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Card Game Models","url":"/methods/category/card-game-models","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"dourn-improving-douzero-by-residual-neural","title":"DouRN: Improving DouZero by Residual Neural Networks","date":"2024-03-21","arxiv_id":"2403.14102","n_code_links":0,"syntology":null},{"paper":"/paper/douzero-improving-doudizhu-ai-by-opponent","slug":"douzero-improving-doudizhu-ai-by-opponent","title":"DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning","date":"2022-04-06","arxiv_id":"2204.02558","n_code_links":1,"syntology":null},{"paper":"/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","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":2,"n_instrument":1,"unverified":3,"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","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"]}}}],"papers_shown":4,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":4,"with_a_code_link":3,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/douzero/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/douzero/papers/ran/1","json":"/method/douzero/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":3},{"task":"/task/card-games","name":"Card Games","papers":2},{"task":"/task/game-of-poker","name":"Game of Poker","papers":1},{"task":"/task/multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning","papers":1},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":1},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":1},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":1}],"tasks_shown":7,"n_tasks":7,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2024","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/douzero"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=DouZero","read_at":"2026-10-05T00:55:14+00:00","query":"DouZero","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"DouZero","origin_arxiv_id":"2106.06135"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2106.06135","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2106.06135","citations":160},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'DouZero'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2106.06135","page":"/paper/douzero-mastering-doudizhu-with-self-play","syntology_url":"https://syntology.ai/paper/2106.06135","in_graph_layer":true,"samples":6,"ran":3,"n_ran_checked":2,"n_instrument":1,"unverified":3,"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","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). This answer is about arXiv:2106.06135, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"b926754a716d99b04adc05df470c32772142fc0155cfb9c43c5981f074dd8da6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}