{"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/the-effects-of-memory-replay-in-reinforcement","title":"The Effects of Memory Replay in Reinforcement Learning","arxiv_id":"1710.06574","date":"2017-10-18","proceeding":null,"authors":["Ruishan Liu","James Zou"],"abstract":"Experience replay is a key technique behind many recent advances in deep\nreinforcement learning. Allowing the agent to learn from earlier memories can\nspeed up learning and break undesirable temporal correlations. Despite its\nwide-spread application, very little is understood about the properties of\nexperience replay. How does the amount of memory kept affect learning dynamics?\nDoes it help to prioritize certain experiences? In this paper, we address these\nquestions by formulating a dynamical systems ODE model of Q-learning with\nexperience replay. We derive analytic solutions of the ODE for a simple\nsetting. We show that even in this very simple setting, the amount of memory\nkept can substantially affect the agent's performance. Too much or too little\nmemory both slow down learning. Moreover, we characterize regimes where\nprioritized replay harms the agent's learning. We show that our analytic\nsolutions have excellent agreement with experiments. Finally, we propose a\nsimple algorithm for adaptively changing the memory buffer size which achieves\nconsistently good empirical performance.","url_abs":"http://arxiv.org/abs/1710.06574v1","url_pdf":"http://arxiv.org/pdf/1710.06574v1.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":"the-effects-of-memory-replay-in-reinforcement","repo_url":"https://github.com/VictorZuanazzi/Project_RL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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":"https://syntology.ai/paper/1710.06574","atlas_url":"https://app.syntology.ai/?focus=1710.06574","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}