{"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/efficient-probabilistic-performance-bounds","title":"Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning","arxiv_id":"1707.00724","date":"2017-07-03","proceeding":null,"authors":["Daniel S. Brown","Scott Niekum"],"abstract":"In the field of reinforcement learning there has been recent progress towards\nsafety and high-confidence bounds on policy performance. However, to our\nknowledge, no practical methods exist for determining high-confidence policy\nperformance bounds in the inverse reinforcement learning setting---where the\ntrue reward function is unknown and only samples of expert behavior are given.\nWe propose a sampling method based on Bayesian inverse reinforcement learning\nthat uses demonstrations to determine practical high-confidence upper bounds on\nthe $\\alpha$-worst-case difference in expected return between any evaluation\npolicy and the optimal policy under the expert's unknown reward function. We\nevaluate our proposed bound on both a standard grid navigation task and a\nsimulated driving task and achieve tighter and more accurate bounds than a\nfeature count-based baseline. We also give examples of how our proposed bound\ncan be utilized to perform risk-aware policy selection and risk-aware policy\nimprovement. Because our proposed bound requires several orders of magnitude\nfewer demonstrations than existing high-confidence bounds, it is the first\npractical method that allows agents that learn from demonstration to express\nconfidence in the quality of their learned policy.","url_abs":"http://arxiv.org/abs/1707.00724v5","url_pdf":"http://arxiv.org/pdf/1707.00724v5.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":"efficient-probabilistic-performance-bounds","repo_url":"https://github.com/dsbrown1331/aaai-2018-code","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"efficient-probabilistic-performance-bounds","repo_url":"https://github.com/archit120/Risk-Aware-Active-IRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"efficient-probabilistic-performance-bounds","repo_url":"https://github.com/dsbrown1331/safe-imitation-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"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":{"atlas_url":"https://app.syntology.ai/?focus=1707.00724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.00724"}},"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/dsbrown1331/safe-imitation-learning","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/archit120/Risk-Aware-Active-IRL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dsbrown1331/aaai-2018-code","reach":{"status":"unanswered"}}],"summary":{"ran_honours":3},"by_repo_kind":{"listed":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"ab0d051f811f37f3","entry":"get_v","repo":"archit120/Risk-Aware-Active-IRL","repo_kind":"listed","path":"alpha_var.py","file_url":"https://github.com/archit120/Risk-Aware-Active-IRL/blob/HEAD/alpha_var.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ab0d051f811f37f3"}},{"code_sha256_prefix":"50fef2dd852d7e5a","entry":"get_v_expert","repo":"archit120/Risk-Aware-Active-IRL","repo_kind":"listed","path":"alpha_var.py","file_url":"https://github.com/archit120/Risk-Aware-Active-IRL/blob/HEAD/alpha_var.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50fef2dd852d7e5a"}},{"code_sha256_prefix":"7d7418b1e6c542e3","entry":"sample_rewards","repo":"archit120/Risk-Aware-Active-IRL","repo_kind":"listed","path":"alpha_var.py","file_url":"https://github.com/archit120/Risk-Aware-Active-IRL/blob/HEAD/alpha_var.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d7418b1e6c542e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}