{"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/dota-2","name":"Dota 2","slug":"dota-2","description_markdown":"Dota 2 is a multiplayer online battle arena (MOBA). The task is to train one-or-more agents to play and win the game.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [OpenAI Five](https://openai.com/five/) )</span>","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":"derived"},"counts":{"papers_tagged":27,"papers_with_code":13,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/video-games","name":"Video Games"}],"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":27,"of":27,"of_with_code":13,"tagged_in_all":27,"counts":{"archive_papers_tagged":27,"with_a_code_link":13,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":27,"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/proximal-policy-optimization-algorithms","slug":"proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","repositories_listed":188,"syntology":{"n":176,"n_ran":99,"n_constructed":53,"n_ran_checked":71,"n_instrument":28,"n_unverified":77,"n_honours":7,"n_violates":2,"n_no_contract":62,"n_pointer_only":94,"phrase":"99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified","sample_list":"/paper/proximal-policy-optimization-algorithms#ran","syntology_url":"https://syntology.ai/paper/1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"}},"official":null}},{"url":"/paper/an-empirical-model-of-large-batch-training","slug":"an-empirical-model-of-large-batch-training","title":"An Empirical Model of Large-Batch Training","date":"2018-12-14","arxiv_id":"1812.06162","repositories_listed":11,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/an-empirical-model-of-large-batch-training#ran","syntology_url":"https://syntology.ai/paper/1812.06162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.06162"}},"official":null}},{"url":"/paper/beyond-the-meta-leveraging-game-design","slug":"beyond-the-meta-leveraging-game-design","title":"Beyond the Meta: Leveraging Game Design Parameters for Patch-Agnostic Esport Analytics","date":"2023-05-29","arxiv_id":"2305.18477","repositories_listed":2,"syntology":null},{"url":"/paper/multi-agent-collaboration-via-reward-1","slug":"multi-agent-collaboration-via-reward-1","title":"Multi-Agent Collaboration via Reward Attribution Decomposition","date":"2020-10-16","arxiv_id":"2010.08531","repositories_listed":2,"syntology":null},{"url":"/paper/context-aware-toxicity-detection-in","slug":"context-aware-toxicity-detection-in","title":"Context-Aware Toxicity Detection in Multiplayer Games: Integrating Domain-Adaptive Pretraining and Match Metadata","date":"2025-04-02","arxiv_id":"2504.01534","repositories_listed":1,"syntology":null},{"url":"/paper/towards-detecting-contextual-real-time","slug":"towards-detecting-contextual-real-time","title":"Towards Detecting Contextual Real-Time Toxicity for In-Game Chat","date":"2023-10-20","arxiv_id":"2310.18330","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-helm-a-human-readable-memory-for-1","slug":"semantic-helm-a-human-readable-memory-for-1","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","date":"2023-06-15","arxiv_id":"2306.09312","repositories_listed":1,"syntology":null},{"url":"/paper/joint-action-loss-for-proximal-policy","slug":"joint-action-loss-for-proximal-policy","title":"Joint action loss for proximal policy optimization","date":"2023-01-26","arxiv_id":"2301.10919","repositories_listed":1,"syntology":null},{"url":"/paper/machine-learning-models-for-dota-2-outcomes","slug":"machine-learning-models-for-dota-2-outcomes","title":"Machine learning models for DOTA 2 outcomes prediction","date":"2021-06-03","arxiv_id":"2106.01782","repositories_listed":1,"syntology":null},{"url":"/paper/tleague-a-framework-for-competitive-self-play","slug":"tleague-a-framework-for-competitive-self-play","title":"TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning","date":"2020-11-25","arxiv_id":"2011.12895","repositories_listed":1,"syntology":null},{"url":"/paper/dota-2-with-large-scale-deep-reinforcement","slug":"dota-2-with-large-scale-deep-reinforcement","title":"Dota 2 with Large Scale Deep Reinforcement Learning","date":"2019-12-13","arxiv_id":"1912.06680","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dota-2-with-large-scale-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1912.06680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.06680"}},"official":null}},{"url":"/paper/time-to-die-death-prediction-in-dota-2-using","slug":"time-to-die-death-prediction-in-dota-2-using","title":"Time to Die: Death Prediction in Dota 2 using Deep Learning","date":"2019-05-21","arxiv_id":"1906.03939","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-esports-match-result-prediction","slug":"real-time-esports-match-result-prediction","title":"Real-time eSports Match Result Prediction","date":"2016-12-10","arxiv_id":"1701.03162","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-pre-trained-language-models-to","slug":"fine-tuning-pre-trained-language-models-to","title":"Fine-Tuning Pre-trained Language Models to Detect In-Game Trash Talks","date":"2024-03-19","arxiv_id":"2403.15458","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimax-exploiter-a-data-efficient-approach","title":"Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play","date":"2023-11-28","arxiv_id":"2311.17190","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-item-recommendation-in-the-moba","title":"Sequential Item Recommendation in the MOBA Game Dota 2","date":"2022-01-17","arxiv_id":"2201.08724","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximum-entropy-model-based-reinforcement","title":"Maximum Entropy Model-based Reinforcement Learning","date":"2021-12-02","arxiv_id":"2112.01195","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-diverse-policies-in-moba-games-via","title":"Learning Diverse Policies in MOBA Games via Macro-Goals","date":"2021-10-27","arxiv_id":"2110.14221","repositories_listed":0,"syntology":null},{"url":null,"slug":"conda-a-contextual-dual-annotated-dataset-for","title":"CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection","date":"2021-06-11","arxiv_id":"2106.06213","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dota-2-bot-competition","title":"The Dota 2 Bot Competition","date":"2021-03-04","arxiv_id":"2103.02943","repositories_listed":0,"syntology":null},{"url":null,"slug":"factored-action-spaces-in-deep-reinforcement","title":"Factored Action Spaces in Deep Reinforcement Learning","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-playing-full-moba-games-with-deep-1","title":"Towards Playing Full MOBA Games with Deep Reinforcement Learning","date":"2020-11-25","arxiv_id":"2011.12692","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-player-identification-in-dota-2","title":"Automatic Player Identification in Dota 2","date":"2020-08-27","arxiv_id":"2008.12401","repositories_listed":0,"syntology":null},{"url":null,"slug":"long-term-planning-and-situational-awareness","title":"Long-Term Planning and Situational Awareness in OpenAI Five","date":"2019-12-13","arxiv_id":"1912.06721","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-surgery-with-sets","title":"Neural Network Surgery with Sets","date":"2019-12-13","arxiv_id":"1912.06719","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-video-highlights-for-yahoo-esports","title":"Real-Time Video Highlights for Yahoo Esports","date":"2016-11-27","arxiv_id":"1611.08780","repositories_listed":0,"syntology":null},{"url":null,"slug":"skill-based-differences-in-spatio-temporal","title":"Skill-Based Differences in Spatio-Temporal Team Behavior in Defence of The Ancients 2","date":"2016-03-24","arxiv_id":"1603.07738","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/dota-2/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/dota-2/papers/ran/1","json":"/task/dota-2/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":"8b13a72e533a828fb2c88af0c550934bc0e8e9a94b7ed5ddd6bc103c97cb5ebc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}