{"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/ddql","slug":"ddql","name":"DDQL","full_name":"Double Deep Q-Learning","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"Deep Reinforcement Learning with Double Q-learning","paper":"/paper/deep-reinforcement-learning-with-double-q","first_author":"Hado van Hasselt","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/deep-reinforcement-learning-with-double-q"},"source":{"url":"http://arxiv.org/abs/1509.06461v3","title":"Deep Reinforcement Learning with Double Q-learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Reinforcement Learning Frameworks","url":"/methods/category/reinforcement-learning-frameworks","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":"/paper/flash-rl-federated-learning-addressing-system","slug":"flash-rl-federated-learning-addressing-system","title":"FLASH-RL: Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learning","date":"2023-11-12","arxiv_id":"2311.06917","n_code_links":1,"syntology":null},{"paper":null,"slug":"privacy-cost-management-in-smart-meters-using","title":"Privacy-Cost Management in Smart Meters Using Deep Reinforcement Learning","date":"2020-03-10","arxiv_id":"2003.04946","n_code_links":0,"syntology":null},{"paper":"/paper/deep-reinforcement-learning-with-double-q","slug":"deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","arxiv_id":"1509.06461","n_code_links":97,"syntology":{"ran":56,"of":106,"n_ran_checked":55,"n_instrument":1,"unverified":50,"pointer_only":57,"phrase":"56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified","official":null}}],"papers_shown":3,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":3,"with_a_code_link":2,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"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":1,"papers_where_code_ran_first_page":"/method/ddql/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/ddql/papers/ran/1","json":"/method/ddql/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":2},{"task":"/task/q-learning","name":"Q-Learning","papers":2},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":2},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":2},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":2},{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/federated-learning","name":"Federated Learning","papers":1},{"task":"/task/management","name":"Management","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2015","papers":1},{"year":"2020","papers":1},{"year":"2023","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/ddql"},"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=DDQL","read_at":"2026-10-05T00:54:32+00:00","query":"DDQL","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":"1509.06461","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 'DDQL' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"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":"0c223ac6f6a0ac340b7403c64151579aeda503b562956407acf65c7ce551b17e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}