{"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/black-box-policy-search-with-probabilistic","title":"Black-Box Policy Search with Probabilistic Programs","arxiv_id":"1507.04635","date":"2015-07-16","proceeding":null,"authors":["Jan-Willem van de Meent","Brooks Paige","David Tolpin","Frank Wood"],"abstract":"In this work, we explore how probabilistic programs can be used to represent\npolicies in sequential decision problems. In this formulation, a probabilistic\nprogram is a black-box stochastic simulator for both the problem domain and the\nagent. We relate classic policy gradient techniques to recently introduced\nblack-box variational methods which generalize to probabilistic program\ninference. We present case studies in the Canadian traveler problem, Rock\nSample, and a benchmark for optimal diagnosis inspired by Guess Who. Each study\nillustrates how programs can efficiently represent policies using moderate\nnumbers of parameters.","url_abs":"http://arxiv.org/abs/1507.04635v4","url_pdf":"http://arxiv.org/pdf/1507.04635v4.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":"black-box-policy-search-with-probabilistic","repo_url":"https://bitbucket.org/probprog/black-box-policy-search","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=1507.04635","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}