{"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/accumulating-eligibility-trace","slug":"accumulating-eligibility-trace","name":"Accumulating Eligibility Trace","full_name":"Accumulating Eligibility Trace","full_name_withheld":false,"description_markdown":"An **Accumulating Eligibility Trace** is a type of [eligibility trace](https://paperswithcode.com/method/eligibility-trace) where the trace increments in an accumulative way. For the memory vector $\\textbf{e}\\_{t} \\in \\mathbb{R}^{b} \\geq \\textbf{0}$:\r\n\r\n$$\\mathbf{e\\_{0}} = \\textbf{0}$$\r\n\r\n$$\\textbf{e}\\_{t} = \\nabla{\\hat{v}}\\left(S\\_{t}, \\mathbf{\\theta}\\_{t}\\right) + \\gamma\\lambda\\textbf{e}\\_{t}$$","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Eligibility Traces","url":"/methods/category/eligibility-traces","pwc_aliases":[]}],"n_papers_tagged":15,"archive_num_papers":15,"papers_newest_first":[{"paper":null,"slug":"on-line-policy-improvement-using-monte-carlo","title":"On-line Policy Improvement using Monte-Carlo Search","date":"2025-01-09","arxiv_id":"2501.05407","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-predictive-control-and-reinforcement-1","title":"Model Predictive Control and Reinforcement Learning: A Unified Framework Based on Dynamic Programming","date":"2024-06-02","arxiv_id":"2406.00592","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-play-starcraft-ii","slug":"large-language-models-play-starcraft-ii","title":"Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach","date":"2023-12-19","arxiv_id":"2312.11865","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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","official":{"repos":["histmeisah/large-language-models-play-starcraftii"],"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"]}}},{"paper":null,"slug":"a-robust-and-opponent-aware-league-training","title":"A Robust and Opponent-Aware League Training Method for StarCraft II","date":"2023-09-21","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/alphastar-unplugged-large-scale-offline","slug":"alphastar-unplugged-large-scale-offline","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","date":"2023-08-07","arxiv_id":"2308.03526","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/on-efficient-reinforcement-learning-for-full","slug":"on-efficient-reinforcement-learning-for-full","title":"On Efficient Reinforcement Learning for Full-length Game of StarCraft II","date":"2022-09-23","arxiv_id":"2209.11553","n_code_links":2,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["liuruoze/hiernet-sc2","liuruoze/mini-AlphaStar"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ai-in-games-techniques-challenges-and","title":"AI in Human-computer Gaming: Techniques, Challenges and Opportunities","date":"2021-11-15","arxiv_id":"2111.07631","n_code_links":0,"syntology":null},{"paper":null,"slug":"search-in-imperfect-information-games","title":"Search in Imperfect Information Games","date":"2021-11-10","arxiv_id":"2111.05884","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-of-alphastar","slug":"rethinking-of-alphastar","title":"Rethinking of AlphaStar","date":"2021-08-07","arxiv_id":"2108.03452","n_code_links":2,"syntology":null},{"paper":"/paper/an-introduction-of-mini-alphastar","slug":"an-introduction-of-mini-alphastar","title":"An Introduction of mini-AlphaStar","date":"2021-04-14","arxiv_id":"2104.06890","n_code_links":1,"syntology":null},{"paper":"/paper/deep-reinforcement-learning-with-function","slug":"deep-reinforcement-learning-with-function","title":"Deep Reinforcement Learning with Function Properties in Mean Reversion Strategies","date":"2021-01-09","arxiv_id":"2101.03418","n_code_links":1,"syntology":null},{"paper":"/paper/tstarbot-x-an-open-sourced-and-comprehensive","slug":"tstarbot-x-an-open-sourced-and-comprehensive","title":"TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game","date":"2020-11-27","arxiv_id":"2011.13729","n_code_links":1,"syntology":null},{"paper":"/paper/forensic-similarity-for-digital-images","slug":"forensic-similarity-for-digital-images","title":"Forensic Similarity for Digital Images","date":"2019-02-13","arxiv_id":"1902.04684","n_code_links":1,"syntology":null},{"paper":null,"slug":"alphastar-an-evolutionary-computation","title":"AlphaStar: An Evolutionary Computation Perspective","date":"2019-02-05","arxiv_id":"1902.01724","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hierarchical-reinforcement-learning-method","title":"A Hierarchical Reinforcement Learning Method for Persistent Time-Sensitive Tasks","date":"2016-06-20","arxiv_id":"1606.06355","n_code_links":0,"syntology":null}],"papers_shown":15,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":15,"with_a_code_link":8,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":15,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":2,"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"},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/method/accumulating-eligibility-trace/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/accumulating-eligibility-trace/papers/ran/1","json":"/method/accumulating-eligibility-trace/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/starcraft-ii","name":"Starcraft II","papers":7},{"task":"/task/starcraft","name":"Starcraft","papers":6},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":5},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":4},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":4},{"task":"/task/decision-making","name":"Decision Making","papers":2},{"task":"/task/ai-agent","name":"AI Agent","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/hierarchical-reinforcement-learning","name":"Hierarchical Reinforcement Learning","papers":1},{"task":"/task/image-forensics","name":"Image Forensics","papers":1},{"task":"/task/image-manipulation-detection","name":"Image Manipulation Detection","papers":1},{"task":"/task/imitation-learning","name":"Imitation Learning","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/model-predictive-control","name":"Model Predictive Control","papers":1},{"task":"/task/offline-rl","name":"Offline RL","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1}],"tasks_shown":19,"n_tasks":19,"usage_by_year":[{"year":"2016","papers":1},{"year":"2019","papers":2},{"year":"2020","papers":1},{"year":"2021","papers":5},{"year":"2022","papers":1},{"year":"2023","papers":3},{"year":"2024","papers":1},{"year":"2025","papers":1}],"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/accumulating-eligibility-trace"},"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=Accumulating%20Eligibility%20Trace","read_at":"2026-10-05T00:51:21+00:00","query":"Accumulating Eligibility Trace","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Accumulating Eligibility Trace' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Selective Eligibility Traces (S-trace)","TRACE","TRACE","TRACE","TRACE","TRACE","TRACE","Trace"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"18f588b519a37ab608b8943263b07837082c074b9bc744adc9125b4d82350348","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}