{"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/is-prioritized-sweeping-the-better-episodic","title":"Is prioritized sweeping the better episodic control?","arxiv_id":"1711.06677","date":"2017-11-20","proceeding":null,"authors":["Johanni Brea"],"abstract":"Episodic control has been proposed as a third approach to reinforcement\nlearning, besides model-free and model-based control, by analogy with the three\ntypes of human memory. i.e. episodic, procedural and semantic memory. But the\ntheoretical properties of episodic control are not well investigated. Here I\nshow that in deterministic tree Markov decision processes, episodic control is\nequivalent to a form of prioritized sweeping in terms of sample efficiency as\nwell as memory and computation demands. For general deterministic and\nstochastic environments, prioritized sweeping performs better even when memory\nand computation demands are restricted to be equal to those of episodic\ncontrol. These results suggest generalizations of prioritized sweeping to\npartially observable environments, its combined use with function approximation\nand the search for possible implementations of prioritized sweeping in brains.","url_abs":"http://arxiv.org/abs/1711.06677v2","url_pdf":"http://arxiv.org/pdf/1711.06677v2.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":"is-prioritized-sweeping-the-better-episodic","repo_url":"https://github.com/jbrea/episodiccontrol","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[{"method_slug":"prioritized-sweeping","method_name":"Prioritized Sweeping"}],"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}