{"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":"/paper/is-q-learning-provably-efficient","title":"Is Q-learning Provably Efficient?","arxiv_id":"1807.03765","date":"2018-07-10","proceeding":"NeurIPS 2018 12","authors":["Chi Jin","Zeyuan Allen-Zhu","Sebastien Bubeck","Michael. I. Jordan"],"abstract":"Model-free reinforcement learning (RL) algorithms, such as Q-learning,\ndirectly parameterize and update value functions or policies without explicitly\nmodeling the environment. They are typically simpler, more flexible to use, and\nthus more prevalent in modern deep RL than model-based approaches. However,\nempirical work has suggested that model-free algorithms may require more\nsamples to learn [Deisenroth and Rasmussen 2011, Schulman et al. 2015]. The\ntheoretical question of \"whether model-free algorithms can be made sample\nefficient\" is one of the most fundamental questions in RL, and remains unsolved\neven in the basic scenario with finitely many states and actions.\n  We prove that, in an episodic MDP setting, Q-learning with UCB exploration\nachieves regret $\\tilde{O}(\\sqrt{H^3 SAT})$, where $S$ and $A$ are the numbers\nof states and actions, $H$ is the number of steps per episode, and $T$ is the\ntotal number of steps. This sample efficiency matches the optimal regret that\ncan be achieved by any model-based approach, up to a single $\\sqrt{H}$ factor.\nTo the best of our knowledge, this is the first analysis in the model-free\nsetting that establishes $\\sqrt{T}$ regret without requiring access to a\n\"simulator.\"","url_abs":"http://arxiv.org/abs/1807.03765v1","url_pdf":"http://arxiv.org/pdf/1807.03765v1.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-q-learning-provably-efficient","repo_url":"https://github.com/microsoft/intrepid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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)"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.03765","atlas_url":"https://app.syntology.ai/?focus=1807.03765","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1807.03765"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1807.03765\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1807.03765"},"call":"get_concepts_for_paper(arxiv_id=\"1807.03765\")"}],"by_repo":[{"repo":"microsoft/intrepid","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"12e7a8e94c170724511d41e457dc0bf167e441b2d432883324f0caf23678afd1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}