{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":100,"tagged_in_all":306,"items":[{"url":"/paper/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_unverified":3,"n_pointer_only":3}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/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","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":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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_unverified":9,"n_pointer_only":5}},{"url":"/paper/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","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","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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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_unverified":6,"n_pointer_only":6}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/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","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","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","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","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":4,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/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","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","title":"Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation","date":"2024-05-31","arxiv_id":"2405.20860","repositories_listed":1,"syntology":null}],"syntology_records":13,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}