{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/prioritized-sweeping","slug":"prioritized-sweeping","name":"Prioritized Sweeping","full_name":"Prioritized Sweeping","full_name_withheld":false,"description_markdown":"**Prioritized Sweeping** is a reinforcement learning technique for model-based algorithms that prioritizes updates according to a measure of urgency, and performs these updates first. A queue is maintained of every state-action pair whose estimated value would change nontrivially if updated, prioritized by the size of the change. When the top pair in the queue is updated, the effect on each of its predecessor pairs is computed. If the effect is greater than some threshold, then the pair is inserted in the queue with the new priority.\r\n\r\nSource: Sutton and Barto, Reinforcement Learning, 2nd Edition","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Efficient Planning","url":"/methods/category/efficient-planning","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":null,"slug":"investigating-the-interplay-of-prioritized","title":"Investigating the Interplay of Prioritized Replay and Generalization","date":"2024-07-12","arxiv_id":"2407.09702","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-based-multi-agent-reinforcement","title":"Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping","date":"2020-01-15","arxiv_id":"2001.07527","n_code_links":0,"syntology":null},{"paper":null,"slug":"reachability-and-differential-based","title":"Reachability and Differential based Heuristics for Solving Markov Decision Processes","date":"2019-01-03","arxiv_id":"1901.00921","n_code_links":0,"syntology":null},{"paper":null,"slug":"prioritized-sweeping-neural-dynaq-with","title":"Prioritized Sweeping Neural DynaQ with Multiple Predecessors, and Hippocampal Replays","date":"2018-02-15","arxiv_id":"1802.05594","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-model-based-deep-reinforcement","slug":"efficient-model-based-deep-reinforcement","title":"Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation","date":"2018-02-12","arxiv_id":"1802.04325","n_code_links":1,"syntology":null},{"paper":"/paper/is-prioritized-sweeping-the-better-episodic","slug":"is-prioritized-sweeping-the-better-episodic","title":"Is prioritized sweeping the better episodic control?","date":"2017-11-20","arxiv_id":"1711.06677","n_code_links":1,"syntology":null}],"papers_shown":6,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":6,"with_a_code_link":2,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":6,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":4},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":3},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":3},{"task":"/task/q-learning","name":"Q-Learning","papers":2},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":1},{"task":null,"name":"Hippocampus","papers":1},{"task":"/task/model-based-reinforcement-learning","name":"Model-based Reinforcement Learning","papers":1},{"task":"/task/multi-agent-reinforcement-learning","name":"Multi-agent Reinforcement Learning","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2017","papers":1},{"year":"2018","papers":2},{"year":"2019","papers":1},{"year":"2020","papers":1},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/prioritized-sweeping"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Prioritized%20Sweeping","read_at":"2026-10-05T01:00:39+00:00","query":"Prioritized Sweeping","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Prioritized Sweeping' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Sweeping*","Prioritized Replay","Sign-Prioritized FL (SP-FL)","PRIORITIZED EXPERIENCE REPLAY","Perception Prioritized Training","Grid-Prioritized Filtering (GPF)","Prioritized Semantic Learning (PSL)","Prioritized Model Experience Replay"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"b0c837d4175c96bffcf9f01e261d66a63e1d35d89d9556001fc0da8cfc801752","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}