{"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/offline-goal-conditioned-reinforcement","title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","arxiv_id":"2403.01734","date":"2024-03-04","proceeding":null,"authors":["Chenyang Cao","Zichen Yan","Renhao Lu","Junbo Tan","Xueqian Wang"],"abstract":"Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these methods encounter limitations when dealing with diverse constraints in complex environments, such as safety constraints. Some of these approaches prioritize goal attainment without considering safety, while others excessively focus on safety at the expense of training efficiency. In this paper, we study the problem of constrained offline GCRL and propose a new method called Recovery-based Supervised Learning (RbSL) to accomplish safety-critical tasks with various goals. To evaluate the method performance, we build a benchmark based on the robot-fetching environment with a randomly positioned obstacle and use expert or random policies to generate an offline dataset. We compare RbSL with three offline GCRL algorithms and one offline safe RL algorithm. As a result, our method outperforms the existing state-of-the-art methods to a large extent. Furthermore, we validate the practicality and effectiveness of RbSL by deploying it on a real Panda manipulator. Code is available at https://github.com/Sunlighted/RbSL.git.","url_abs":"https://arxiv.org/abs/2403.01734v1","url_pdf":"https://arxiv.org/pdf/2403.01734v1.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":"offline-goal-conditioned-reinforcement","repo_url":"https://github.com/sunlighted/rbsl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.01734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01734"}},"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/sunlighted/rbsl","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_honours":2,"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"cf5ce98955ab4534","entry":"atanh","repo":"sunlighted/rbsl","repo_kind":"official","path":"rl_modules/models.py","file_url":"https://github.com/sunlighted/rbsl/blob/HEAD/rl_modules/models.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cf5ce98955ab4534"}},{"code_sha256_prefix":"b6113e0f43155a33","entry":"cosine_beta_schedule","repo":"sunlighted/rbsl","repo_kind":"official","path":"rl_modules/helpers.py","file_url":"https://github.com/sunlighted/rbsl/blob/HEAD/rl_modules/helpers.py","link_basis":"harvester_set","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":"b6113e0f43155a33"}},{"code_sha256_prefix":"6eb59c36d3f33fe4","entry":"goal_distance","repo":"sunlighted/rbsl","repo_kind":"official","path":"rl_modules/base_agent.py","file_url":"https://github.com/sunlighted/rbsl/blob/HEAD/rl_modules/base_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6eb59c36d3f33fe4"}},{"code_sha256_prefix":"63d21c7afce1a9e5","entry":"linear_beta_schedule","repo":"sunlighted/rbsl","repo_kind":"official","path":"rl_modules/helpers.py","file_url":"https://github.com/sunlighted/rbsl/blob/HEAD/rl_modules/helpers.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63d21c7afce1a9e5"}},{"code_sha256_prefix":"09c8479d9a5b3e06","entry":"extract","repo":"sunlighted/rbsl","repo_kind":"official","path":"rl_modules/helpers.py","file_url":"https://github.com/sunlighted/rbsl/blob/HEAD/rl_modules/helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"09c8479d9a5b3e06"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}