{"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/revisiting-prioritized-experience-replay-a-1","title":"Revisiting Prioritized Experience Replay: A Value Perspective","arxiv_id":"2102.03261","date":"2021-02-05","proceeding":null,"authors":["Ang A. Li","Zongqing Lu","Chenglin Miao"],"abstract":"Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs experiences by the magnitude of their temporal-difference error ($|\\text{TD}|$) significantly improves the learning efficiency. But how $|\\text{TD}|$ is related to the importance of experience is not well understood. We address this problem from an economic perspective, by linking $|\\text{TD}|$ to value of experience, which is defined as the value added to the cumulative reward by accessing the experience. We theoretically show the value metrics of experience are upper-bounded by $|\\text{TD}|$ for Q-learning. Furthermore, we successfully extend our theoretical framework to maximum-entropy RL by deriving the lower and upper bounds of these value metrics for soft Q-learning, which turn out to be the product of $|\\text{TD}|$ and \"on-policyness\" of the experiences. Our framework links two important quantities in RL: $|\\text{TD}|$ and value of experience. We empirically show that the bounds hold in practice, and experience replay using the upper bound as priority improves maximum-entropy RL in Atari games.","url_abs":"https://arxiv.org/abs/2102.03261v1","url_pdf":"https://arxiv.org/pdf/2102.03261v1.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":"revisiting-prioritized-experience-replay-a-1","repo_url":"https://github.com/AmazingAng/VER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"revisiting-prioritized-experience-replay-a-1","repo_url":"https://github.com/RLforlife/VER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"prioritized-experience-replay","method_name":"Prioritized Experience Replay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}