{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/should-all-temporal-difference-learning-use","title":"Should All Temporal Difference Learning Use Emphasis?","arxiv_id":"1903.00194","date":"2019-03-01","proceeding":null,"authors":["Xiang Gu","Sina Ghiassian","Richard S. Sutton"],"abstract":"Emphatic Temporal Difference (ETD) learning has recently been proposed as a\nconvergent off-policy learning method. ETD was proposed mainly to address\nconvergence issues of conventional Temporal Difference (TD) learning under\noff-policy training but it is different from conventional TD learning even\nunder on-policy training. A simple counterexample provided back in 2017 pointed\nto a potential class of problems where ETD converges but TD diverges. In this\npaper, we empirically show that ETD converges on a few other well-known\non-policy experiments whereas TD either diverges or performs poorly. We also\nshow that ETD outperforms TD on the mountain car prediction problem. Our\nresults, together with a similar pattern observed under off-policy training in\nprior works, suggest that ETD might be a good substitute over conventional TD.","url_abs":"http://arxiv.org/abs/1903.00194v1","url_pdf":"http://arxiv.org/pdf/1903.00194v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"should-all-temporal-difference-learning-use","repo_url":"https://github.com/Xiang-Gu/Should-ALL-Temporal-Difference-Learning-Use-Emphasis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}