{"total":20,"rows":[{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"area":null},{"id":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56,"area":null},{"id":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"area":null},{"id":"2209.07133","title":"COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checking","created":"2022-09-15","cited_by_count":19,"area":null},{"id":"2112.05198","title":"Reinforcement Learning with Almost Sure Constraints","created":"2021-12-09","cited_by_count":11,"area":null},{"id":"2112.09655","title":"Distillation of RL Policies with Formal Guarantees via Variational Abstraction of Markov Decision Processes (Technical Report)","created":"2021-12-17","cited_by_count":9,"area":null},{"id":"2408.03093","title":"Certifiably Robust Policies for Uncertain Parametric Environments","created":"2024-08-06","cited_by_count":7,"area":null},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2211.15349","title":"Shielding in Resource-Constrained Goal POMDPs","created":"2022-11-28","cited_by_count":4,"area":null},{"id":"2301.11592","title":"Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties","created":"2023-01-27","cited_by_count":4,"area":null},{"id":"2305.00889","title":"The Impact of the Geometric Properties of the Constraint Set in Safe Optimization with Bandit Feedback","created":"2023-05-01","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":"2605.10888","title":"Shields to Guarantee Probabilistic Safety in MDPs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.01339","title":"Robust Parameter Learning for Uncertain MDPs","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2103.01413","title":"Safe Learning of Uncertain Environments","created":"2021-03-02","cited_by_count":0,"area":null},{"id":"2303.12558","title":"Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2304.03081","title":"Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2407.11471","title":"Safe Online Convex Optimization with Multi-Point Feedback","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2603.02396","title":"COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management","created":"2026-03-02","cited_by_count":0,"area":null}],"next_cursor":null}