{"url":"/method/true-online-td-lambda","slug":"true-online-td-lambda","name":"True Online TD Lambda","full_name":"True Online TD Lambda","full_name_withheld":false,"description_markdown":"**True Online $TD\\left(\\lambda\\right)$** seeks to approximate the ideal online $\\lambda$-return algorithm. It seeks to invert this ideal forward-view algorithm to produce an efficient backward-view algorithm using eligibility traces. It uses dutch traces rather than accumulating traces.\r\n\r\nSource: [Sutton and Seijen](http://proceedings.mlr.press/v32/seijen14.pdf)","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":"On-Policy TD Control","url":"/methods/category/on-policy-td-control","pwc_aliases":[]}],"n_papers_tagged":0,"archive_num_papers":0,"papers_newest_first":[],"papers_shown":0,"tasks":[],"tasks_shown":0,"n_tasks":0,"usage_by_year":[],"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/true-online-td-lambda"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}