{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/safe-reinforcement-learning","name":"Safe Reinforcement Learning","slug":"safe-reinforcement-learning","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":306,"papers_with_code":100,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/safe-control-gym","name":"safe-control-gym","full_name":"","num_papers_in_archive":6}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":306,"of_with_code":100,"tagged_in_all":306,"counts":{"archive_papers_tagged":306,"with_a_code_link":100,"where_syntology_ran_a_sample":34,"not_listed_spam_title":0,"listed":306,"listed_where_code_ran":34,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":26,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":26,"listed_every_run_a_failure_of_syntologys_instrument":8,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/constrained-policy-optimization","slug":"constrained-policy-optimization","title":"Constrained Policy Optimization","date":"2017-05-30","arxiv_id":"1705.10528","repositories_listed":10,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/constrained-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/1705.10528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.10528"}},"official":null}},{"url":"/paper/safe-learning-in-robotics-from-learning-based","slug":"safe-learning-in-robotics-from-learning-based","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","date":"2021-08-13","arxiv_id":"2108.06266","repositories_listed":5,"syntology":null},{"url":"/paper/balance-reward-and-safety-optimization-for","slug":"balance-reward-and-safety-optimization-for","title":"Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation","date":"2024-05-02","arxiv_id":"2405.01677","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/balance-reward-and-safety-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2405.01677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01677"}},"official":{"repos":["saferl-lab/safety-mujoco","pku-alignment/omnisafe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/datasets-and-benchmarks-for-offline-safe","slug":"datasets-and-benchmarks-for-offline-safe","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","date":"2023-06-15","arxiv_id":"2306.09303","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/datasets-and-benchmarks-for-offline-safe#ran","syntology_url":"https://syntology.ai/paper/2306.09303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.09303"}},"official":{"repos":["liuzuxin/dsrl","liuzuxin/fsrl","liuzuxin/osrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/constrained-update-projection-approach-to","slug":"constrained-update-projection-approach-to","title":"Constrained Update Projection Approach to Safe Policy Optimization","date":"2022-09-15","arxiv_id":"2209.07089","repositories_listed":3,"syntology":null},{"url":"/paper/feasible-actor-critic-constrained","slug":"feasible-actor-critic-constrained","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","date":"2021-05-22","arxiv_id":"2105.10682","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/feasible-actor-critic-constrained#ran","syntology_url":"https://syntology.ai/paper/2105.10682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.10682"}},"official":{"repos":["mahaitongdae/Feasible-Actor-Critic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/off-policy-primal-dual-safe-reinforcement","slug":"off-policy-primal-dual-safe-reinforcement","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","date":"2024-01-26","arxiv_id":"2401.14758","repositories_listed":2,"syntology":{"n":22,"n_ran":13,"n_constructed":1,"n_ran_checked":9,"n_instrument":4,"n_unverified":9,"n_honours":2,"n_violates":2,"n_no_contract":5,"n_pointer_only":10,"phrase":"13 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 2 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/off-policy-primal-dual-safe-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2401.14758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14758"}},"official":{"repos":["pku-alignment/omnisafe","zifanwu/cal"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/nlbac-a-neural-ordinary-differential","slug":"nlbac-a-neural-ordinary-differential","title":"Stable and Safe Human-aligned Reinforcement Learning through Neural Ordinary Differential Equations","date":"2024-01-23","arxiv_id":"2401.13148","repositories_listed":2,"syntology":null},{"url":"/paper/self-improving-safety-performance-of","slug":"self-improving-safety-performance-of","title":"Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms","date":"2022-10-29","arxiv_id":"2210.16575","repositories_listed":2,"syntology":null},{"url":"/paper/log-barriers-for-safe-black-box-optimization","slug":"log-barriers-for-safe-black-box-optimization","title":"Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning","date":"2022-07-21","arxiv_id":"2207.10415","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/log-barriers-for-safe-black-box-optimization#ran","syntology_url":"https://syntology.ai/paper/2207.10415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10415"}},"official":{"repos":["ilnura/lb_sgd","lasgroup/lbsgd-rl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reachability-constrained-reinforcement","slug":"reachability-constrained-reinforcement","title":"Reachability Constrained Reinforcement Learning","date":"2022-05-16","arxiv_id":"2205.07536","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reachability-constrained-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2205.07536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.07536"}},"official":{"repos":["mahaitongdae/Reachability_Constrained_RL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/constrained-variational-policy-optimization","slug":"constrained-variational-policy-optimization","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","date":"2022-01-28","arxiv_id":"2201.11927","repositories_listed":2,"syntology":{"n":11,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/constrained-variational-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2201.11927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11927"}},"official":{"repos":["liuzuxin/cvpo-safe-rl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/metadrive-composing-diverse-driving-scenarios","slug":"metadrive-composing-diverse-driving-scenarios","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","date":"2021-09-26","arxiv_id":"2109.12674","repositories_listed":2,"syntology":null},{"url":"/paper/recovery-rl-safe-reinforcement-learning-with","slug":"recovery-rl-safe-reinforcement-learning-with","title":"Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones","date":"2020-10-29","arxiv_id":"2010.15920","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recovery-rl-safe-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2010.15920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15920"}},"official":null}},{"url":"/paper/safe-reinforcement-learning-with-scene","slug":"safe-reinforcement-learning-with-scene","title":"Safe Reinforcement Learning with Scene Decomposition for Navigating Complex Urban Environments","date":"2019-04-25","arxiv_id":"1904.11483","repositories_listed":2,"syntology":null},{"url":"/paper/2506-08266","slug":"2506-08266","title":"Reinforcement Learning from Human Feedback with High-Confidence Safety Constraints","date":"2025-06-09","arxiv_id":"2506.08266","repositories_listed":1,"syntology":null},{"url":"/paper/safe-multi-agent-navigation-guided-by-goal","slug":"safe-multi-agent-navigation-guided-by-goal","title":"Safe Multi-Agent Navigation guided by Goal-Conditioned Safe Reinforcement Learning","date":"2025-02-25","arxiv_id":"2502.17813","repositories_listed":1,"syntology":null},{"url":"/paper/risk-averse-reinforcement-learning-an-optimal","slug":"risk-averse-reinforcement-learning-an-optimal","title":"Risk-Averse Reinforcement Learning: An Optimal Transport Perspective on Temporal Difference Learning","date":"2025-02-22","arxiv_id":"2502.16328","repositories_listed":1,"syntology":null},{"url":"/paper/constraint-adaptive-policy-switching-for","slug":"constraint-adaptive-policy-switching-for","title":"Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning","date":"2024-12-25","arxiv_id":"2412.18946","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/constraint-adaptive-policy-switching-for#ran","syntology_url":"https://syntology.ai/paper/2412.18946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18946"}},"official":{"repos":["yassinech/caps"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/offline-safe-reinforcement-learning-using","slug":"offline-safe-reinforcement-learning-using","title":"Offline Safe Reinforcement Learning Using Trajectory Classification","date":"2024-12-19","arxiv_id":"2412.15429","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/offline-safe-reinforcement-learning-using#ran","syntology_url":"https://syntology.ai/paper/2412.15429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15429"}},"official":{"repos":["zgong11/TraC"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tilted-quantile-gradient-updates-for-quantile","slug":"tilted-quantile-gradient-updates-for-quantile","title":"Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning","date":"2024-12-17","arxiv_id":"2412.13184","repositories_listed":1,"syntology":null},{"url":"/paper/latent-safety-constrained-policy-approach-for","slug":"latent-safety-constrained-policy-approach-for","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","date":"2024-12-11","arxiv_id":"2412.08794","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/latent-safety-constrained-policy-approach-for#ran","syntology_url":"https://syntology.ai/paper/2412.08794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08794"}},"official":{"repos":["PrajwalKoirala/LSPC-Safe-Offline-RL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/marvel-accelerating-safe-online-reinforcement","slug":"marvel-accelerating-safe-online-reinforcement","title":"Marvel: Accelerating Safe Online Reinforcement Learning with Finetuned Offline Policy","date":"2024-12-05","arxiv_id":"2412.04426","repositories_listed":1,"syntology":null},{"url":"/paper/think-smart-act-smarl-analyzing-probabilistic","slug":"think-smart-act-smarl-analyzing-probabilistic","title":"Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning","date":"2024-11-07","arxiv_id":"2411.04867","repositories_listed":1,"syntology":null},{"url":"/paper/handling-long-term-safety-and-uncertainty-in","slug":"handling-long-term-safety-and-uncertainty-in","title":"Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning","date":"2024-09-18","arxiv_id":"2409.12045","repositories_listed":1,"syntology":null},{"url":"/paper/real-world-validation-of-safe-reinforcement","slug":"real-world-validation-of-safe-reinforcement","title":"Real-world validation of safe reinforcement learning, model predictive control and decision tree-based home energy management systems","date":"2024-08-14","arxiv_id":"2408.07435","repositories_listed":1,"syntology":null},{"url":"/paper/oasis-conditional-distribution-shaping-for","slug":"oasis-conditional-distribution-shaping-for","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","date":"2024-07-19","arxiv_id":"2407.14653","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/oasis-conditional-distribution-shaping-for#ran","syntology_url":"https://syntology.ai/paper/2407.14653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14653"}},"official":{"repos":["yihangyao/OASIS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/transductive-active-learning-with-application","slug":"transductive-active-learning-with-application","title":"Transductive Active Learning with Application to Safe Bayesian Optimization","date":"2024-07-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/commonpower-supercharging-machine-learning","slug":"commonpower-supercharging-machine-learning","title":"CommonPower: A Framework for Safe Data-Driven Smart Grid Control","date":"2024-06-05","arxiv_id":"2406.03231","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-efficiency-of-safe-reinforcement","slug":"enhancing-efficiency-of-safe-reinforcement","title":"Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation","date":"2024-05-31","arxiv_id":"2405.20860","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-in-black-box","slug":"safe-reinforcement-learning-in-black-box","title":"Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding","date":"2024-05-28","arxiv_id":"2405.18180","repositories_listed":1,"syntology":null},{"url":"/paper/verified-safe-reinforcement-learning-for","slug":"verified-safe-reinforcement-learning-for","title":"Verified Safe Reinforcement Learning for Neural Network Dynamic Models","date":"2024-05-25","arxiv_id":"2405.15994","repositories_listed":1,"syntology":null},{"url":"/paper/feasibility-consistent-representation","slug":"feasibility-consistent-representation","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","date":"2024-05-20","arxiv_id":"2405.11718","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/feasibility-consistent-representation#ran","syntology_url":"https://syntology.ai/paper/2405.11718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11718"}},"official":{"repos":["czp16/fcsrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/from-representational-harms-to-quality-of","slug":"from-representational-harms-to-quality-of","title":"From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards","date":"2024-03-20","arxiv_id":"2403.13213","repositories_listed":1,"syntology":null},{"url":"/paper/policy-bifurcation-in-safe-reinforcement","slug":"policy-bifurcation-in-safe-reinforcement","title":"Policy Bifurcation in Safe Reinforcement Learning","date":"2024-03-19","arxiv_id":"2403.12847","repositories_listed":1,"syntology":null},{"url":"/paper/sampling-based-safe-reinforcement-learning","slug":"sampling-based-safe-reinforcement-learning","title":"Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems","date":"2024-03-06","arxiv_id":"2403.04007","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-approximate-model-based-shielding","slug":"leveraging-approximate-model-based-shielding","title":"Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments","date":"2024-02-01","arxiv_id":"2402.00816","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-system-level-safety-in-mixed","slug":"enhancing-system-level-safety-in-mixed","title":"Enhancing System-Level Safety in Mixed-Autonomy Platoon via Safe Reinforcement Learning","date":"2024-01-20","arxiv_id":"2401.11148","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-in-uncertain","slug":"safe-reinforcement-learning-in-uncertain","title":"Safe reinforcement learning in uncertain contexts","date":"2024-01-11","arxiv_id":"2401.05876","repositories_listed":1,"syntology":null},{"url":"/paper/imitate-the-good-and-avoid-the-bad-an","slug":"imitate-the-good-and-avoid-the-bad-an","title":"Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning","date":"2023-12-16","arxiv_id":"2312.10385","repositories_listed":1,"syntology":null},{"url":"/paper/state-wise-safe-reinforcement-learning-with","slug":"state-wise-safe-reinforcement-learning-with","title":"State-Wise Safe Reinforcement Learning With Pixel Observations","date":"2023-11-03","arxiv_id":"2311.02227","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/state-wise-safe-reinforcement-learning-with#ran","syntology_url":"https://syntology.ai/paper/2311.02227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02227"}},"official":{"repos":["simonzhan-code/step-wise_saferl_pixel"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-framework-for-interpretable-and","slug":"hierarchical-framework-for-interpretable-and","title":"Hierarchical Framework for Interpretable and Probabilistic Model-Based Safe Reinforcement Learning","date":"2023-10-28","arxiv_id":"2310.18811","repositories_listed":1,"syntology":null},{"url":"/paper/safe-rlhf-safe-reinforcement-learning-from","slug":"safe-rlhf-safe-reinforcement-learning-from","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","date":"2023-10-19","arxiv_id":"2310.12773","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-rlhf-safe-reinforcement-learning-from#ran","syntology_url":"https://syntology.ai/paper/2310.12773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12773"}},"official":{"repos":["pku-alignment/safe-rlhf"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/specialized-deep-residual-policy-safe","slug":"specialized-deep-residual-policy-safe","title":"Specialized Deep Residual Policy Safe Reinforcement Learning-Based Controller for Complex and Continuous State-Action Spaces","date":"2023-10-15","arxiv_id":"2310.14788","repositories_listed":1,"syntology":null},{"url":"/paper/safe-deep-policy-adaptation","slug":"safe-deep-policy-adaptation","title":"Safe Deep Policy Adaptation","date":"2023-10-08","arxiv_id":"2310.08602","repositories_listed":1,"syntology":null},{"url":"/paper/approximate-model-based-shielding-for-safe","slug":"approximate-model-based-shielding-for-safe","title":"Approximate Model-Based Shielding for Safe Reinforcement Learning","date":"2023-07-27","arxiv_id":"2308.00707","repositories_listed":1,"syntology":null},{"url":"/paper/safe-dreamerv3-safe-reinforcement-learning","slug":"safe-dreamerv3-safe-reinforcement-learning","title":"SafeDreamer: Safe Reinforcement Learning with World Models","date":"2023-07-14","arxiv_id":"2307.07176","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":2,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 2 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/safe-dreamerv3-safe-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2307.07176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07176"}},"official":{"repos":["pku-alignment/safedreamer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-as-wasserstein","slug":"safe-reinforcement-learning-as-wasserstein","title":"Probabilistic Constrained Reinforcement Learning with Formal Interpretability","date":"2023-07-13","arxiv_id":"2307.07084","repositories_listed":1,"syntology":null},{"url":"/paper/rosarl-reward-only-safe-reinforcement","slug":"rosarl-reward-only-safe-reinforcement","title":"ROSARL: Reward-Only Safe Reinforcement Learning","date":"2023-05-31","arxiv_id":"2306.00035","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/rosarl-reward-only-safe-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2306.00035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00035"}},"official":{"repos":["geraudnt/rosarl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/guard-a-safe-reinforcement-learning-benchmark","slug":"guard-a-safe-reinforcement-learning-benchmark","title":"GUARD: A Safe Reinforcement Learning Benchmark","date":"2023-05-23","arxiv_id":"2305.13681","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/guard-a-safe-reinforcement-learning-benchmark#ran","syntology_url":"https://syntology.ai/paper/2305.13681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13681"}},"official":{"repos":["intelligent-control-lab/guard"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/omnisafe-an-infrastructure-for-accelerating","slug":"omnisafe-an-infrastructure-for-accelerating","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","date":"2023-05-16","arxiv_id":"2305.09304","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-energy-system-scheduling-using-a","slug":"optimal-energy-system-scheduling-using-a","title":"Optimal Energy System Scheduling Using A Constraint-Aware Reinforcement Learning Algorithm","date":"2023-05-09","arxiv_id":"2305.05484","repositories_listed":1,"syntology":null},{"url":"/paper/a-barrier-lyapunov-actor-critic-reinforcement","slug":"a-barrier-lyapunov-actor-critic-reinforcement","title":"Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach","date":"2023-04-08","arxiv_id":"2304.04066","repositories_listed":1,"syntology":null},{"url":"/paper/a-multiplicative-value-function-for-safe-and","slug":"a-multiplicative-value-function-for-safe-and","title":"A Multiplicative Value Function for Safe and Efficient Reinforcement Learning","date":"2023-03-07","arxiv_id":"2303.04118","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-via-probabilistic","slug":"safe-reinforcement-learning-via-probabilistic","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","date":"2023-03-06","arxiv_id":"2303.03226","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/safe-reinforcement-learning-via-probabilistic#ran","syntology_url":"https://syntology.ai/paper/2303.03226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.03226"}},"official":null}},{"url":"/paper/constrained-decision-transformer-for-offline","slug":"constrained-decision-transformer-for-offline","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","date":"2023-02-14","arxiv_id":"2302.07351","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/constrained-decision-transformer-for-offline#ran","syntology_url":"https://syntology.ai/paper/2302.07351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.07351"}},"official":{"repos":["liuzuxin/osrl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/optimal-transport-perturbations-for-safe","slug":"optimal-transport-perturbations-for-safe","title":"Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees","date":"2023-01-31","arxiv_id":"2301.13375","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-trust-region-based-safe","slug":"efficient-trust-region-based-safe","title":"Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints","date":"2023-01-26","arxiv_id":"2301.10923","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficient-trust-region-based-safe#ran","syntology_url":"https://syntology.ai/paper/2301.10923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.10923"}},"official":{"repos":["rllab-snu/safe-distributional-actor-critic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explainable-and-safe-reinforcement-learning","slug":"explainable-and-safe-reinforcement-learning","title":"Explainable and Safe Reinforcement Learning for Autonomous Air Mobility","date":"2022-11-24","arxiv_id":"2211.13474","repositories_listed":1,"syntology":null},{"url":"/paper/safelight-a-reinforcement-learning-method","slug":"safelight-a-reinforcement-learning-method","title":"SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control","date":"2022-11-20","arxiv_id":"2211.10871","repositories_listed":1,"syntology":null},{"url":"/paper/provable-safe-reinforcement-learning-with","slug":"provable-safe-reinforcement-learning-with","title":"Provable Safe Reinforcement Learning with Binary Feedback","date":"2022-10-26","arxiv_id":"2210.14492","repositories_listed":1,"syntology":null},{"url":"/paper/model-based-safe-deep-reinforcement-learning","slug":"model-based-safe-deep-reinforcement-learning","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","date":"2022-10-14","arxiv_id":"2210.07573","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/model-based-safe-deep-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2210.07573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07573"}},"official":{"repos":["akjayant/mbppol"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-model-based-reinforcement-learning-with-2","slug":"safe-model-based-reinforcement-learning-with-2","title":"Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate","date":"2022-10-14","arxiv_id":"2210.07553","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/safe-model-based-reinforcement-learning-with-2#ran","syntology_url":"https://syntology.ai/paper/2210.07553","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07553"}},"official":{"repos":["ManUtdMoon/Safe_MBRL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-from-pixels-using","slug":"safe-reinforcement-learning-from-pixels-using","title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","date":"2022-10-02","arxiv_id":"2210.01801","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/safe-reinforcement-learning-from-pixels-using#ran","syntology_url":"https://syntology.ai/paper/2210.01801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01801"}},"official":{"repos":["safe-slac/safe-slac"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/saferl-kit-evaluating-efficient-reinforcement","slug":"saferl-kit-evaluating-efficient-reinforcement","title":"SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving","date":"2022-06-17","arxiv_id":"2206.08528","repositories_listed":1,"syntology":null},{"url":"/paper/towards-safe-reinforcement-learning-via-2","slug":"towards-safe-reinforcement-learning-via-2","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk","date":"2022-06-09","arxiv_id":"2206.04436","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-robustness-of-safe-reinforcement","slug":"on-the-robustness-of-safe-reinforcement","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","date":"2022-05-29","arxiv_id":"2205.14691","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-the-robustness-of-safe-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2205.14691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14691"}},"official":{"repos":["liuzuxin/safe-rl-robustness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-review-of-safe-reinforcement-learning","slug":"a-review-of-safe-reinforcement-learning","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","date":"2022-05-20","arxiv_id":"2205.10330","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-using-black-box","slug":"safe-reinforcement-learning-using-black-box","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","date":"2022-04-15","arxiv_id":"2204.07417","repositories_listed":1,"syntology":null},{"url":"/paper/cup-a-conservative-update-policy-algorithm-1","slug":"cup-a-conservative-update-policy-algorithm-1","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","date":"2022-02-15","arxiv_id":"2202.07565","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-by-imagining-the-1","slug":"safe-reinforcement-learning-by-imagining-the-1","title":"Safe Reinforcement Learning by Imagining the Near Future","date":"2022-02-15","arxiv_id":"2202.07789","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/safe-reinforcement-learning-by-imagining-the-1#ran","syntology_url":"https://syntology.ai/paper/2202.07789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.07789"}},"official":{"repos":["gwthomas/safe-mbpo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/saute-rl-almost-surely-safe-reinforcement","slug":"saute-rl-almost-surely-safe-reinforcement","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","date":"2022-02-14","arxiv_id":"2202.06558","repositories_listed":1,"syntology":null},{"url":"/paper/towards-safe-reinforcement-learning-with-a","slug":"towards-safe-reinforcement-learning-with-a","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","date":"2022-01-28","arxiv_id":"2201.12427","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-safe-reinforcement-learning-with-a#ran","syntology_url":"https://syntology.ai/paper/2201.12427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12427"}},"official":{"repos":["hnyu/seditor"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/conservative-and-adaptive-penalty-for-model","slug":"conservative-and-adaptive-penalty-for-model","title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning","date":"2021-12-14","arxiv_id":"2112.07701","repositories_listed":1,"syntology":null},{"url":"/paper/safe-exploration-for-constrained","slug":"safe-exploration-for-constrained","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","date":"2021-12-01","arxiv_id":"2112.00885","repositories_listed":1,"syntology":null},{"url":"/paper/safe-model-based-reinforcement-learning-using","slug":"safe-model-based-reinforcement-learning-using","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","date":"2021-10-11","arxiv_id":"2110.05415","repositories_listed":1,"syntology":null},{"url":"/paper/learning-barrier-certificates-towards-safe","slug":"learning-barrier-certificates-towards-safe","title":"Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations","date":"2021-08-04","arxiv_id":"2108.01846","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-barrier-certificates-towards-safe#ran","syntology_url":"https://syntology.ai/paper/2108.01846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.01846"}},"official":{"repos":["roosephu/crabs"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/how-to-certify-machine-learning-based-safety","slug":"how-to-certify-machine-learning-based-safety","title":"How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review","date":"2021-07-26","arxiv_id":"2107.12045","repositories_listed":1,"syntology":null},{"url":"/paper/towards-safe-reinforcement-learning-via-1","slug":"towards-safe-reinforcement-learning-via-1","title":"Towards Safe Reinforcement Learning via Constraining Conditional Value at Risk","date":"2021-06-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-using-advantage","slug":"safe-reinforcement-learning-using-advantage","title":"Safe Reinforcement Learning Using Advantage-Based Intervention","date":"2021-06-16","arxiv_id":"2106.09110","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-reinforcement-learning-using-advantage#ran","syntology_url":"https://syntology.ai/paper/2106.09110","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09110"}},"official":{"repos":["nolanwagener/safe_rl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/model-based-safe-reinforcement-learning-using","slug":"model-based-safe-reinforcement-learning-using","title":"Model-based Constrained Reinforcement Learning using Generalized Control Barrier Function","date":"2021-03-02","arxiv_id":"2103.01556","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/model-based-safe-reinforcement-learning-using#ran","syntology_url":"https://syntology.ai/paper/2103.01556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01556"}},"official":{"repos":["mahaitongdae/safe_exp_env"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unifying-cardiovascular-modelling-with-deep","slug":"unifying-cardiovascular-modelling-with-deep","title":"Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment","date":"2021-01-21","arxiv_id":"2101.08477","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unifying-cardiovascular-modelling-with-deep#ran","syntology_url":"https://syntology.ai/paper/2101.08477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.08477"}},"official":{"repos":["thxsxth/POMDP_RLSepsis"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/safe-model-based-reinforcement-learning-with-1","slug":"safe-model-based-reinforcement-learning-with-1","title":"Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method","date":"2020-10-15","arxiv_id":"2010.07968","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-in-constrained","slug":"safe-reinforcement-learning-in-constrained","title":"Safe Reinforcement Learning in Constrained Markov Decision Processes","date":"2020-08-15","arxiv_id":"2008.06626","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safe-reinforcement-learning-in-constrained#ran","syntology_url":"https://syntology.ai/paper/2008.06626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.06626"}},"official":{"repos":["akifumi-wachi-4/safe_near_optimal_mdp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-via-curriculum","slug":"safe-reinforcement-learning-via-curriculum","title":"Safe Reinforcement Learning via Curriculum Induction","date":"2020-06-22","arxiv_id":"2006.12136","repositories_listed":1,"syntology":null},{"url":"/paper/samba-safe-model-based-active-reinforcement","slug":"samba-safe-model-based-active-reinforcement","title":"SAMBA: Safe Model-Based & Active Reinforcement Learning","date":"2020-06-12","arxiv_id":"2006.09436","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-of-control-affine","slug":"safe-reinforcement-learning-of-control-affine","title":"Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks","date":"2020-03-20","arxiv_id":"2003.09488","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-for-probabilistic","slug":"safe-reinforcement-learning-for-probabilistic","title":"Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach","date":"2020-02-24","arxiv_id":"2002.10126","repositories_listed":1,"syntology":null},{"url":"/paper/convergent-policy-optimization-for-safe","slug":"convergent-policy-optimization-for-safe","title":"Convergent Policy Optimization for Safe Reinforcement Learning","date":"2019-10-26","arxiv_id":"1910.12156","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-for-temporal-logic","slug":"reinforcement-learning-for-temporal-logic","title":"Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees","date":"2019-09-11","arxiv_id":"1909.05304","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-for-temporal-logic#ran","syntology_url":"https://syntology.ai/paper/1909.05304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.05304"}},"official":{"repos":["grockious/lcrl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-reinforcement-learning-via-online","slug":"safe-reinforcement-learning-via-online","title":"Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding","date":"2019-05-25","arxiv_id":"1905.10691","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-safe-reinforcement-learning","slug":"end-to-end-safe-reinforcement-learning","title":"End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks","date":"2019-03-21","arxiv_id":"1903.08792","repositories_listed":1,"syntology":null},{"url":"/paper/certified-reinforcement-learning-with-logic","slug":"certified-reinforcement-learning-with-logic","title":"Certified Reinforcement Learning with Logic Guidance","date":"2019-02-02","arxiv_id":"1902.00778","repositories_listed":1,"syntology":null},{"url":"/paper/better-safe-than-sorry-evidence-accumulation","slug":"better-safe-than-sorry-evidence-accumulation","title":"Better Safe than Sorry: Evidence Accumulation Allows for Safe Reinforcement Learning","date":"2018-09-24","arxiv_id":"1809.09147","repositories_listed":1,"syntology":null},{"url":"/paper/reward-constrained-policy-optimization","slug":"reward-constrained-policy-optimization","title":"Reward Constrained Policy Optimization","date":"2018-05-28","arxiv_id":"1805.11074","repositories_listed":1,"syntology":null},{"url":"/paper/a-lyapunov-based-approach-to-safe","slug":"a-lyapunov-based-approach-to-safe","title":"A Lyapunov-based Approach to Safe Reinforcement Learning","date":"2018-05-20","arxiv_id":"1805.07708","repositories_listed":1,"syntology":null},{"url":"/paper/logically-constrained-reinforcement-learning","slug":"logically-constrained-reinforcement-learning","title":"Logically-Constrained Reinforcement Learning","date":"2018-01-24","arxiv_id":"1801.08099","repositories_listed":1,"syntology":null},{"url":"/paper/safe-reinforcement-learning-via-shielding","slug":"safe-reinforcement-learning-via-shielding","title":"Safe Reinforcement Learning via Shielding","date":"2017-08-29","arxiv_id":"1708.08611","repositories_listed":1,"syntology":null},{"url":"/paper/trial-without-error-towards-safe","slug":"trial-without-error-towards-safe","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","date":"2017-07-17","arxiv_id":"1707.05173","repositories_listed":1,"syntology":null},{"url":"/paper/data-efficient-reinforcement-learning-with","slug":"data-efficient-reinforcement-learning-with","title":"Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control","date":"2017-06-20","arxiv_id":"1706.06491","repositories_listed":1,"syntology":null}],"syntology_records":34,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":34,"papers_where_code_ran_first_page":"/task/safe-reinforcement-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/safe-reinforcement-learning/papers/2","json":"/task/safe-reinforcement-learning/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/safe-reinforcement-learning/papers/3","json":"/task/safe-reinforcement-learning/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/safe-reinforcement-learning/papers/4","json":"/task/safe-reinforcement-learning/papers/4.json","rows":6},{"order":"ran","page":1,"of":1,"url":"/task/safe-reinforcement-learning/papers/ran/1","json":"/task/safe-reinforcement-learning/papers/ran/1.json","rows":34}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"8f13ff5026d3b06861c8243196eae8a70334dc6e4245ce931c07a4acf42e2092","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}