{"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/optimizing-expectation-with-guarantees-in","title":"Optimizing Expectation with Guarantees in POMDPs (Technical Report)","arxiv_id":"1611.08696","date":"2016-11-26","proceeding":null,"authors":["Krishnendu Chatterjee","Petr Novotný","Guillermo A. Pérez","Jean-François Raskin","Đorđe Žikelić"],"abstract":"A standard objective in partially-observable Markov decision processes\n(POMDPs) is to find a policy that maximizes the expected discounted-sum payoff.\nHowever, such policies may still permit unlikely but highly undesirable\noutcomes, which is problematic especially in safety-critical applications.\nRecently, there has been a surge of interest in POMDPs where the goal is to\nmaximize the probability to ensure that the payoff is at least a given\nthreshold, but these approaches do not consider any optimization beyond\nsatisfying this threshold constraint. In this work we go beyond both the\n\"expectation\" and \"threshold\" approaches and consider a \"guaranteed payoff\noptimization (GPO)\" problem for POMDPs, where we are given a threshold $t$ and\nthe objective is to find a policy $\\sigma$ such that a) each possible outcome\nof $\\sigma$ yields a discounted-sum payoff of at least $t$, and b) the expected\ndiscounted-sum payoff of $\\sigma$ is optimal (or near-optimal) among all\npolicies satisfying a). We present a practical approach to tackle the GPO\nproblem and evaluate it on standard POMDP benchmarks.","url_abs":"http://arxiv.org/abs/1611.08696v2","url_pdf":"http://arxiv.org/pdf/1611.08696v2.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":"optimizing-expectation-with-guarantees-in","repo_url":"https://github.com/gaperez64/GPOMCP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.08696","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}