{"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/log-barriers-for-safe-black-box-optimization","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","arxiv_id":"2207.10415","date":"2022-07-21","proceeding":null,"authors":["Ilnura Usmanova","Yarden As","Maryam Kamgarpour","Andreas Krause"],"abstract":"Optimizing noisy functions online, when evaluating the objective requires experiments on a deployed system, is a crucial task arising in manufacturing, robotics and many others. Often, constraints on safe inputs are unknown ahead of time, and we only obtain noisy information, indicating how close we are to violating the constraints. Yet, safety must be guaranteed at all times, not only for the final output of the algorithm. We introduce a general approach for seeking a stationary point in high dimensional non-linear stochastic optimization problems in which maintaining safety during learning is crucial. Our approach called LB-SGD is based on applying stochastic gradient descent (SGD) with a carefully chosen adaptive step size to a logarithmic barrier approximation of the original problem. We provide a complete convergence analysis of non-convex, convex, and strongly-convex smooth constrained problems, with first-order and zeroth-order feedback. Our approach yields efficient updates and scales better with dimensionality compared to existing approaches. We empirically compare the sample complexity and the computational cost of our method with existing safe learning approaches. Beyond synthetic benchmarks, we demonstrate the effectiveness of our approach on minimizing constraint violation in policy search tasks in safe reinforcement learning (RL).","url_abs":"https://arxiv.org/abs/2207.10415v2","url_pdf":"https://arxiv.org/pdf/2207.10415v2.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":"log-barriers-for-safe-black-box-optimization","repo_url":"https://github.com/ilnura/lb_sgd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"log-barriers-for-safe-black-box-optimization","repo_url":"https://github.com/lasgroup/lbsgd-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"safe-reinforcement-learning","task_name":"Safe Reinforcement Learning"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.10415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10415"}},"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/ilnura/lb_sgd","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lasgroup/lbsgd-rl","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":"ad474d258a0848be","entry":"resolve_name","repo":"lasgroup/lbsgd-rl","repo_kind":"official","path":"lbsgd_rl/plot.py","file_url":"https://github.com/lasgroup/lbsgd-rl/blob/HEAD/lbsgd_rl/plot.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad474d258a0848be"}},{"code_sha256_prefix":"49a8afc10f8c9abf","entry":"make_statistics","repo":"lasgroup/lbsgd-rl","repo_kind":"official","path":"lbsgd_rl/plot.py","file_url":"https://github.com/lasgroup/lbsgd-rl/blob/HEAD/lbsgd_rl/plot.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":"49a8afc10f8c9abf"}},{"code_sha256_prefix":"559663b333800999","entry":"median_percentiles","repo":"lasgroup/lbsgd-rl","repo_kind":"official","path":"lbsgd_rl/plot.py","file_url":"https://github.com/lasgroup/lbsgd-rl/blob/HEAD/lbsgd_rl/plot.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":"559663b333800999"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}