{"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/popcorn-partially-observed-prediction","title":"POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning","arxiv_id":"2001.04032","date":"2020-01-13","proceeding":null,"authors":["Joseph Futoma","Michael C. Hughes","Finale Doshi-Velez"],"abstract":"Many medical decision-making tasks can be framed as partially observed Markov decision processes (POMDPs). However, prevailing two-stage approaches that first learn a POMDP and then solve it often fail because the model that best fits the data may not be well suited for planning. We introduce a new optimization objective that (a) produces both high-performing policies and high-quality generative models, even when some observations are irrelevant for planning, and (b) does so in batch off-policy settings that are typical in healthcare, when only retrospective data is available. We demonstrate our approach on synthetic examples and a challenging medical decision-making problem.","url_abs":"https://arxiv.org/abs/2001.04032v2","url_pdf":"https://arxiv.org/pdf/2001.04032v2.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":"popcorn-partially-observed-prediction","repo_url":"https://github.com/dtak/POPCORN-POMDP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"prediction","task_name":"Prediction"},{"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":{"syntology_url":"https://syntology.ai/paper/2001.04032","atlas_url":"https://app.syntology.ai/?focus=2001.04032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04032"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dtak/POPCORN-POMDP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":4},"by_repo_kind":{"official":{"samples":11,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"3f4c74055a033cb3","entry":"adam","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f4c74055a033cb3"}},{"code_sha256_prefix":"90d6acc349d5d069","entry":"create_single_tiger_env","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/envs_cts.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/envs_cts.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90d6acc349d5d069"}},{"code_sha256_prefix":"c00386e85af0f104","entry":"create_tiger_env","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/envs_cts.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/envs_cts.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c00386e85af0f104"}},{"code_sha256_prefix":"230b81c32b380299","entry":"create_tiger_witness","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/envs_cts.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/envs_cts.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"230b81c32b380299"}},{"code_sha256_prefix":"071e3368add1eecb","entry":"gd_nag","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"071e3368add1eecb"}},{"code_sha256_prefix":"79562521f7728505","entry":"lighten_color","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/tiger_gmm_results.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/tiger_gmm_results.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79562521f7728505"}},{"code_sha256_prefix":"b8ed706b3e8f98d4","entry":"rprop","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8ed706b3e8f98d4"}},{"code_sha256_prefix":"c559371632c6a9fe","entry":"get_padded_beh_probs_from_IDs","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/util_hypotension.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/util_hypotension.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c559371632c6a9fe"}},{"code_sha256_prefix":"3fa8b94273bbed0b","entry":"get_padded_databatch_from_IDs","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/util_hypotension.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/util_hypotension.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fa8b94273bbed0b"}},{"code_sha256_prefix":"1b85f7b4f3581d2a","entry":"params_init","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/param_inits.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/param_inits.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b85f7b4f3581d2a"}},{"code_sha256_prefix":"dac6be100b0250f0","entry":"random_MLP_param_inits","repo":"dtak/POPCORN-POMDP","repo_kind":"official","path":"src/util_hypotension.py","file_url":"https://github.com/dtak/POPCORN-POMDP/blob/HEAD/src/util_hypotension.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dac6be100b0250f0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}