{"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/posterior-sampling-for-reinforcement-learning-1","title":"Posterior Sampling for Reinforcement Learning Without Episodes","arxiv_id":"1608.02731","date":"2016-08-09","proceeding":null,"authors":["Ian Osband","Benjamin Van Roy"],"abstract":"This is a brief technical note to clarify some of the issues with applying\nthe application of the algorithm posterior sampling for reinforcement learning\n(PSRL) in environments without fixed episodes. In particular, this paper aims\nto:\n  - Review some of results which have been proven for finite horizon MDPs\n(Osband et al 2013, 2014a, 2014b, 2016) and also for MDPs with finite ergodic\nstructure (Gopalan et al 2014).\n  - Review similar results for optimistic algorithms in infinite horizon\nproblems (Jaksch et al 2010, Bartlett and Tewari 2009, Abbasi-Yadkori and\nSzepesvari 2011), with particular attention to the dynamic episode growth.\n  - Highlight the delicate technical issue which has led to a fault in the\nproof of the lazy-PSRL algorithm (Abbasi-Yadkori and Szepesvari 2015). We\npresent an explicit counterexample to this style of argument. Therefore, we\nsuggest that the Theorem 2 in (Abbasi-Yadkori and Szepesvari 2015) be instead\nconsidered a conjecture, as it has no rigorous proof.\n  - Present pragmatic approaches to apply PSRL in infinite horizon problems. We\nconjecture that, under some additional assumptions, it will be possible to\nobtain bounds $O( \\sqrt{T} )$ even without episodic reset.\n  We hope that this note serves to clarify existing results in the field of\nreinforcement learning and provides interesting motivation for future work.","url_abs":"http://arxiv.org/abs/1608.02731v1","url_pdf":"http://arxiv.org/pdf/1608.02731v1.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":"posterior-sampling-for-reinforcement-learning-1","repo_url":"https://github.com/stratismarkou/sample-efficient-bayesian-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.02731","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}