{"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/learning-to-play-in-a-day-faster-deep","title":"Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening","arxiv_id":"1611.01606","date":"2016-11-05","proceeding":null,"authors":["Frank S. He","Yang Liu","Alexander G. Schwing","Jian Peng"],"abstract":"We propose a novel training algorithm for reinforcement learning which\ncombines the strength of deep Q-learning with a constrained optimization\napproach to tighten optimality and encourage faster reward propagation. Our\nnovel technique makes deep reinforcement learning more practical by drastically\nreducing the training time. We evaluate the performance of our approach on the\n49 games of the challenging Arcade Learning Environment, and report significant\nimprovements in both training time and accuracy.","url_abs":"http://arxiv.org/abs/1611.01606v1","url_pdf":"http://arxiv.org/pdf/1611.01606v1.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":"learning-to-play-in-a-day-faster-deep","repo_url":"https://github.com/suyoung-lee/Episodic-Backward-Update","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1611.01606","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}