{"total":20,"rows":[{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60,"area":null},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"area":null},{"id":"2302.04375","title":"A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints","created":"2023-02-08","cited_by_count":17,"area":null},{"id":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"2111.06978","title":"RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN","created":"2021-11-12","cited_by_count":15,"area":null},{"id":"2112.05198","title":"Reinforcement Learning with Almost Sure Constraints","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2210.14492","title":"Provable Safe Reinforcement Learning with Binary Feedback","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2301.11547","title":"Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation","created":"2023-01-27","cited_by_count":6,"area":null},{"id":"2207.04117","title":"Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents","created":"2022-07-08","cited_by_count":5,"area":null},{"id":"2306.00035","title":"ROSARL: Reward-Only Safe Reinforcement Learning","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2404.05424","title":"What Are the Odds? Improving the foundations of Statistical Model Checking","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2205.15376","title":"Reinforcement Learning with a Terminator","created":"2022-05-30","cited_by_count":4,"area":null},{"id":"2301.02389","title":"Provable Reset-free Reinforcement Learning by No-Regret Reduction","created":"2023-01-06","cited_by_count":3,"area":null},{"id":"2105.08748","title":"Learning to Act Safely with Limited Exposure and Almost Sure Certainty","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2307.15910","title":"Reinforcement Learning Under Probabilistic Spatio-Temporal Constraints with Time Windows","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2310.16363","title":"Finite-Time Analysis of Three-Timescale Constrained Actor-Critic and Constrained Natural Actor-Critic Algorithms","created":"2023-10-25","cited_by_count":2,"area":null},{"id":"2202.11593","title":"Finding Safe Zones of policies Markov Decision Processes","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2410.23637","title":"Anytime-Constrained Equilibria in Polynomial Time","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2505.07101","title":"Constrained Online Decision-Making: A Unified Framework","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2109.09855","title":"Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits","created":"2021-09-20","cited_by_count":0,"area":null}],"next_cursor":null}