{"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/safe-policy-optimization-with-local","title":"Safe Policy Optimization with Local Generalized Linear Function Approximations","arxiv_id":"2111.04894","date":"2021-11-09","proceeding":"NeurIPS 2021 12","authors":["Akifumi Wachi","Yunyue Wei","Yanan Sui"],"abstract":"Safe exploration is a key to applying reinforcement learning (RL) in safety-critical systems. Existing safe exploration methods guaranteed safety under the assumption of regularity, and it has been difficult to apply them to large-scale real problems. We propose a novel algorithm, SPO-LF, that optimizes an agent's policy while learning the relation between a locally available feature obtained by sensors and environmental reward/safety using generalized linear function approximations. We provide theoretical guarantees on its safety and optimality. We experimentally show that our algorithm is 1) more efficient in terms of sample complexity and computational cost and 2) more applicable to large-scale problems than previous safe RL methods with theoretical guarantees, and 3) comparably sample-efficient and safer compared with existing advanced deep RL methods with safety constraints.","url_abs":"https://arxiv.org/abs/2111.04894v1","url_pdf":"https://arxiv.org/pdf/2111.04894v1.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":"safe-policy-optimization-with-local","repo_url":"https://github.com/akifumi-wachi-4/spolf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"safe-exploration","task_name":"Safe Exploration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.04894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.04894"}},"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":"deterministic:regex_extraction","url":"https://github.com/openai/safety-starter-agents","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/akifumi-wachi-4/spolf","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"17b3b9854d998de1","entry":"check_path","repo":"akifumi-wachi-4/spolf","repo_kind":"official","path":"safety_gym_discrete/myenv/generate_env.py","file_url":"https://github.com/akifumi-wachi-4/spolf/blob/HEAD/safety_gym_discrete/myenv/generate_env.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":false,"mcp_get_code":{"code_sha256":"17b3b9854d998de1"}},{"code_sha256_prefix":"46093266ed178a1e","entry":"coord_to_safety_gym_pos","repo":"akifumi-wachi-4/spolf","repo_kind":"official","path":"safety_gym_discrete/baseline/run_exp.py","file_url":"https://github.com/akifumi-wachi-4/spolf/blob/HEAD/safety_gym_discrete/baseline/run_exp.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":false,"mcp_get_code":{"code_sha256":"46093266ed178a1e"}},{"code_sha256_prefix":"200ca87c801110ce","entry":"coord_to_safety_gym_pos","repo":"akifumi-wachi-4/spolf","repo_kind":"official","path":"safety_gym_discrete/myenv/safety_gym_discrete.py","file_url":"https://github.com/akifumi-wachi-4/spolf/blob/HEAD/safety_gym_discrete/myenv/safety_gym_discrete.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":false,"mcp_get_code":{"code_sha256":"200ca87c801110ce"}},{"code_sha256_prefix":"0b5515bfc28abdd3","entry":"safety_gym_pos_to_coord","repo":"akifumi-wachi-4/spolf","repo_kind":"official","path":"safety_gym_discrete/baseline/run_exp.py","file_url":"https://github.com/akifumi-wachi-4/spolf/blob/HEAD/safety_gym_discrete/baseline/run_exp.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":false,"mcp_get_code":{"code_sha256":"0b5515bfc28abdd3"}},{"code_sha256_prefix":"0a12b5db6d9c17a0","entry":"safety_gym_pos_to_coord","repo":"akifumi-wachi-4/spolf","repo_kind":"official","path":"safety_gym_discrete/myenv/safety_gym_discrete.py","file_url":"https://github.com/akifumi-wachi-4/spolf/blob/HEAD/safety_gym_discrete/myenv/safety_gym_discrete.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":false,"mcp_get_code":{"code_sha256":"0a12b5db6d9c17a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}