{"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/guard-a-safe-reinforcement-learning-benchmark","title":"GUARD: A Safe Reinforcement Learning Benchmark","arxiv_id":"2305.13681","date":"2023-05-23","proceeding":null,"authors":["WeiYe Zhao","Yifan Sun","Feihan Li","Rui Chen","Ruixuan Liu","Tianhao Wei","Changliu Liu"],"abstract":"Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety-critical real-world applications, such as autonomous driving, human-robot interaction, robot manipulation, etc, where such errors are not tolerable. Recently, safe RL (i.e. constrained RL) has emerged rapidly in the literature, in which the agents explore the environment while satisfying constraints. Due to the diversity of algorithms and tasks, it remains difficult to compare existing safe RL algorithms. To fill that gap, we introduce GUARD, a Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD has several advantages compared to existing benchmarks. First, GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. Second, GUARD comprehensively covers state-of-the-art safe RL algorithms with self-contained implementations. Third, GUARD is highly customizable in tasks and algorithms. We present a comparison of state-of-the-art safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.","url_abs":"https://arxiv.org/abs/2305.13681v4","url_pdf":"https://arxiv.org/pdf/2305.13681v4.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":"guard-a-safe-reinforcement-learning-benchmark","repo_url":"https://github.com/intelligent-control-lab/guard","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"safe-reinforcement-learning","task_name":"Safe Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.13681","atlas_url":"https://app.syntology.ai/?focus=2305.13681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13681"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/intelligent-control-lab/guard","reach":null}],"summary":{"ran_honours":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"07702efbfb3b4a00","entry":"auto_grad","repo":"intelligent-control-lab/guard","repo_kind":"official","path":"safe_rl_lib/cpo/cpo.py","file_url":"https://github.com/intelligent-control-lab/guard/blob/HEAD/safe_rl_lib/cpo/cpo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07702efbfb3b4a00"}},{"code_sha256_prefix":"c49c1432a1f5bace","entry":"cg","repo":"intelligent-control-lab/guard","repo_kind":"official","path":"safe_rl_lib/cpo/cpo.py","file_url":"https://github.com/intelligent-control-lab/guard/blob/HEAD/safe_rl_lib/cpo/cpo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c49c1432a1f5bace"}},{"code_sha256_prefix":"303c89c7fabb88a9","entry":"get_net_param_np_vec","repo":"intelligent-control-lab/guard","repo_kind":"official","path":"safe_rl_lib/cpo/cpo.py","file_url":"https://github.com/intelligent-control-lab/guard/blob/HEAD/safe_rl_lib/cpo/cpo.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"303c89c7fabb88a9"}},{"code_sha256_prefix":"a8a0b894b36fb9b6","entry":"normalize","repo":"intelligent-control-lab/guard","repo_kind":"official","path":"safe_rl_envs/safe_rl_envs/bench/bench_utils.py","file_url":"https://github.com/intelligent-control-lab/guard/blob/HEAD/safe_rl_envs/safe_rl_envs/bench/bench_utils.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8a0b894b36fb9b6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}