{"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/constrained-policy-optimization-via-bayesian-1","title":"Constrained Policy Optimization via Bayesian World Models","arxiv_id":"2201.09802","date":"2022-01-24","proceeding":"ICLR 2022 4","authors":["Yarden As","Ilnura Usmanova","Sebastian Curi","Andreas Krause"],"abstract":"Improving sample-efficiency and safety are crucial challenges when deploying reinforcement learning in high-stakes real world applications. We propose LAMBDA, a novel model-based approach for policy optimization in safety critical tasks modeled via constrained Markov decision processes. Our approach utilizes Bayesian world models, and harnesses the resulting uncertainty to maximize optimistic upper bounds on the task objective, as well as pessimistic upper bounds on the safety constraints. We demonstrate LAMBDA's state of the art performance on the Safety-Gym benchmark suite in terms of sample efficiency and constraint violation.","url_abs":"https://arxiv.org/abs/2201.09802v4","url_pdf":"https://arxiv.org/pdf/2201.09802v4.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":"constrained-policy-optimization-via-bayesian-1","repo_url":"https://github.com/yardenas/la-mbda","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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=2201.09802","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.09802"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/yardenas/la-mbda","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":12},"by_repo_kind":{"official":{"samples":12,"ran":0,"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":"7c19fbe757803123","entry":"compute_lambda_values","repo":"yardenas/la-mbda","repo_kind":"official","path":"la_mbda/utils.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/la_mbda/utils.py","link_basis":"harvester_set","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":"7c19fbe757803123"}},{"code_sha256_prefix":"8551e6debd395f0f","entry":"do_episode","repo":"yardenas/la-mbda","repo_kind":"official","path":"la_mbda/utils.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/la_mbda/utils.py","link_basis":"harvester_set","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":"8551e6debd395f0f"}},{"code_sha256_prefix":"28cf454f15d83008","entry":"encoder","repo":"yardenas/la-mbda","repo_kind":"official","path":"la_mbda/building_blocks.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/la_mbda/building_blocks.py","link_basis":"harvester_set","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":"28cf454f15d83008"}},{"code_sha256_prefix":"2b604df9c4ee01a3","entry":"gather_optimistic_pessimistic_sample","repo":"yardenas/la-mbda","repo_kind":"official","path":"la_mbda/la_mbda.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/la_mbda/la_mbda.py","link_basis":"harvester_set","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":"2b604df9c4ee01a3"}},{"code_sha256_prefix":"fb06e5e4d7fa71e8","entry":"gather_optimistic_sample","repo":"yardenas/la-mbda","repo_kind":"official","path":"la_mbda/la_mbda.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/la_mbda/la_mbda.py","link_basis":"harvester_set","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":"fb06e5e4d7fa71e8"}},{"code_sha256_prefix":"247ea75588da9af8","entry":"interact","repo":"yardenas/la-mbda","repo_kind":"official","path":"la_mbda/utils.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/la_mbda/utils.py","link_basis":"harvester_set","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":"247ea75588da9af8"}},{"code_sha256_prefix":"51ae64821a5fdcd2","entry":"make_dm_env","repo":"yardenas/la-mbda","repo_kind":"official","path":"la_mbda/env_wrappers.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/la_mbda/env_wrappers.py","link_basis":"harvester_set","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":"51ae64821a5fdcd2"}},{"code_sha256_prefix":"e62fa20f2534e99c","entry":"make_gym_env","repo":"yardenas/la-mbda","repo_kind":"official","path":"la_mbda/env_wrappers.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/la_mbda/env_wrappers.py","link_basis":"harvester_set","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":"e62fa20f2534e99c"}},{"code_sha256_prefix":"0dd6945d470eaed0","entry":"make_summary","repo":"yardenas/la-mbda","repo_kind":"official","path":"experiments/train_utils.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/experiments/train_utils.py","link_basis":"harvester_set","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":"0dd6945d470eaed0"}},{"code_sha256_prefix":"98a9e65f4e16e687","entry":"numerical_sort","repo":"yardenas/la-mbda","repo_kind":"official","path":"experiments/plot.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/experiments/plot.py","link_basis":"harvester_set","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":"98a9e65f4e16e687"}},{"code_sha256_prefix":"d7d477df4bbd828d","entry":"parse","repo":"yardenas/la-mbda","repo_kind":"official","path":"experiments/plot.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/experiments/plot.py","link_basis":"harvester_set","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":"d7d477df4bbd828d"}},{"code_sha256_prefix":"5eb0a160c03e94fd","entry":"parse_tf_event_file","repo":"yardenas/la-mbda","repo_kind":"official","path":"experiments/plot.py","file_url":"https://github.com/yardenas/la-mbda/blob/HEAD/experiments/plot.py","link_basis":"harvester_set","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":"5eb0a160c03e94fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}