{"url":"/task/safe-exploration","name":"Safe Exploration","slug":"safe-exploration","description_markdown":"**Safe Exploration** is an approach to collect ground truth data by safely interacting with the environment.\n\n\n<span class=\"description-source\">Source: [Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems ](https://arxiv.org/abs/2005.04374)</span>","categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":135,"papers_with_code":43,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"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":43,"tagged_in_all":135,"items":[{"url":"/paper/safe-exploration-in-continuous-action-spaces","title":"Safe Exploration in Continuous Action Spaces","date":"2018-01-26","arxiv_id":"1801.08757","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"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/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/safeml-safety-monitoring-of-machine-learning","title":"SafeML: Safety Monitoring of Machine Learning Classifiers through Statistical Difference Measure","date":"2020-05-27","arxiv_id":"2005.13166","repositories_listed":2,"syntology":null},{"url":"/paper/ai-safety-gridworlds","title":"AI Safety Gridworlds","date":"2017-11-27","arxiv_id":"1711.09883","repositories_listed":2,"syntology":null},{"url":"/paper/confidence-guided-human-ai-collaboration","title":"Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving","date":"2025-06-04","arxiv_id":"2506.03568","repositories_listed":1,"syntology":null},{"url":"/paper/conrft-a-reinforced-fine-tuning-method-for","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","date":"2025-02-08","arxiv_id":"2502.05450","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"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/exterior-penalty-policy-optimization-with","title":"Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints","date":"2024-07-22","arxiv_id":"2407.15537","repositories_listed":1,"syntology":null},{"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/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/a-comparison-of-rl-based-and-pid-controllers","title":"A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking","date":"2024-01-29","arxiv_id":"2401.16618","repositories_listed":1,"syntology":null},{"url":"/paper/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_unverified":2,"n_pointer_only":14}},{"url":"/paper/probabilistic-counterexample-guidance-for","title":"Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)","date":"2023-07-10","arxiv_id":"2307.04927","repositories_listed":1,"syntology":null},{"url":"/paper/safe-and-sample-efficient-reinforcement","title":"Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments","date":"2023-03-24","arxiv_id":"2303.14265","repositories_listed":1,"syntology":null},{"url":"/paper/information-theoretic-safe-exploration-with","title":"Information-Theoretic Safe Exploration with Gaussian Processes","date":"2022-12-09","arxiv_id":"2212.04914","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":8}},{"url":"/paper/benefits-of-monotonicity-in-safe-exploration","title":"Benefits of Monotonicity in Safe Exploration with Gaussian Processes","date":"2022-11-03","arxiv_id":"2211.01561","repositories_listed":1,"syntology":null},{"url":"/paper/atlas-automate-online-service-configuration","title":"Atlas: Automate Online Service Configuration in Network Slicing","date":"2022-10-30","arxiv_id":"2210.16902","repositories_listed":1,"syntology":null},{"url":"/paper/the-pump-scheduling-problem-a-real-world","title":"The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning","date":"2022-10-20","arxiv_id":"2210.11111","repositories_listed":1,"syntology":null},{"url":"/paper/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":5,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/near-optimal-multi-agent-learning-for-safe","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","date":"2022-10-12","arxiv_id":"2210.06380","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/safe-exploration-method-for-reinforcement","title":"Safe Exploration Method for Reinforcement Learning under Existence of Disturbance","date":"2022-09-30","arxiv_id":"2209.15452","repositories_listed":1,"syntology":null},{"url":"/paper/toward-safe-and-accelerated-deep","title":"Toward Safe and Accelerated Deep Reinforcement Learning for Next-Generation Wireless Networks","date":"2022-09-16","arxiv_id":"2209.13532","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-safe-exploration-using-safety-state","title":"Effects of Safety State Augmentation on Safe Exploration","date":"2022-06-06","arxiv_id":"2206.02675","repositories_listed":1,"syntology":null},{"url":"/paper/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/scalable-safe-exploration-for-global","title":"GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems","date":"2022-01-24","arxiv_id":"2201.09562","repositories_listed":1,"syntology":null},{"url":"/paper/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-policy-optimization-with-local","title":"Safe Policy Optimization with Local Generalized Linear Function Approximations","date":"2021-11-09","arxiv_id":"2111.04894","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":5}},{"url":"/paper/infinite-time-horizon-safety-of-bayesian","title":"Infinite Time Horizon Safety of Bayesian Neural Networks","date":"2021-11-04","arxiv_id":"2111.03165","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/safe-continuous-control-with-constrained","title":"Safe Continuous Control with Constrained Model-Based Policy Optimization","date":"2021-04-14","arxiv_id":"2104.06922","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}}],"syntology_records":10,"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"}}