{"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,"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,"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","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,"unverified":0,"pointer_only":2}},{"paper":null,"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","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,"unverified":0,"pointer_only":0}},{"paper":"/paper/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":0,"of":10,"unverified":10,"pointer_only":0}},{"paper":null,"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,"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","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","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","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","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","title":"Forensic Similarity for Digital Images","date":"2019-02-13","arxiv_id":"1902.04684","n_code_links":1,"syntology":null},{"paper":null,"title":"AlphaStar: An Evolutionary Computation Perspective","date":"2019-02-05","arxiv_id":"1902.01724","n_code_links":0,"syntology":null},{"paper":null,"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,"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":"2026-09-24T18:15:14+00:00"}