{"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/reducing-safety-interventions-in-provably","title":"Reducing Safety Interventions in Provably Safe Reinforcement Learning","arxiv_id":"2303.03339","date":"2023-03-06","proceeding":null,"authors":["Jakob Thumm","Guillaume Pelat","Matthias Althoff"],"abstract":"Deep Reinforcement Learning (RL) has shown promise in addressing complex robotic challenges. In real-world applications, RL is often accompanied by failsafe controllers as a last resort to avoid catastrophic events. While necessary for safety, these interventions can result in undesirable behaviors, such as abrupt braking or aggressive steering. This paper proposes two safety intervention reduction methods: proactive replacement and proactive projection, which change the action of the agent if it leads to a potential failsafe intervention. These approaches are compared to state-of-the-art constrained RL on the OpenAI safety gym benchmark and a human-robot collaboration task. Our study demonstrates that the combination of our method with provably safe RL leads to high-performing policies with zero safety violations and a low number of failsafe interventions. Our versatile method can be applied to a wide range of real-world robotic tasks, while effectively improving safety without sacrificing task performance.","url_abs":"https://arxiv.org/abs/2303.03339v2","url_pdf":"https://arxiv.org/pdf/2303.03339v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"reducing-safety-interventions-in-provably","repo_url":"https://github.com/jakobthumm/safety-intervention-reduction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.03339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03339"}},"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/jakobthumm/safety-intervention-reduction","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":"d7740644bf4b7de1","entry":"normalize","repo":"jakobthumm/safety-intervention-reduction","repo_kind":"official","path":"Safety_Gym/safety_gym/bench/bench_utils.py","file_url":"https://github.com/jakobthumm/safety-intervention-reduction/blob/HEAD/Safety_Gym/safety_gym/bench/bench_utils.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":"d7740644bf4b7de1"}},{"code_sha256_prefix":"4ac8031d738ec401","entry":"quat2zalign","repo":"jakobthumm/safety-intervention-reduction","repo_kind":"official","path":"Safety_Gym/safety_gym/envs/engine.py","file_url":"https://github.com/jakobthumm/safety-intervention-reduction/blob/HEAD/Safety_Gym/safety_gym/envs/engine.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":"4ac8031d738ec401"}},{"code_sha256_prefix":"39708d407531ef32","entry":"theta2vec","repo":"jakobthumm/safety-intervention-reduction","repo_kind":"official","path":"Safety_Gym/safety_gym/envs/engine.py","file_url":"https://github.com/jakobthumm/safety-intervention-reduction/blob/HEAD/Safety_Gym/safety_gym/envs/engine.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":"39708d407531ef32"}},{"code_sha256_prefix":"9a58a6bb8dccddd3","entry":"convert","repo":"jakobthumm/safety-intervention-reduction","repo_kind":"official","path":"Safety_Gym/safety_gym/envs/world.py","file_url":"https://github.com/jakobthumm/safety-intervention-reduction/blob/HEAD/Safety_Gym/safety_gym/envs/world.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":"9a58a6bb8dccddd3"}},{"code_sha256_prefix":"57c952fdc1ca4a15","entry":"infill_info","repo":"jakobthumm/safety-intervention-reduction","repo_kind":"official","path":"rlpyt/projects/safe/safety_gym_env.py","file_url":"https://github.com/jakobthumm/safety-intervention-reduction/blob/HEAD/rlpyt/projects/safe/safety_gym_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":true,"mcp_get_code":{"code_sha256":"57c952fdc1ca4a15"}},{"code_sha256_prefix":"b8083402c3d64e26","entry":"rot2quat","repo":"jakobthumm/safety-intervention-reduction","repo_kind":"official","path":"Safety_Gym/safety_gym/envs/world.py","file_url":"https://github.com/jakobthumm/safety-intervention-reduction/blob/HEAD/Safety_Gym/safety_gym/envs/world.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":"b8083402c3d64e26"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}