{"total":31,"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":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61,"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":"2102.12855","title":"Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic","created":"2021-02-24","cited_by_count":39,"area":null},{"id":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"area":null},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2210.10691","title":"Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes","created":"2022-10-19","cited_by_count":26,"area":null},{"id":"2210.05308","title":"Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees","created":"2022-10-11","cited_by_count":23,"area":null},{"id":"2212.01861","title":"Online Shielding for Reinforcement Learning","created":"2022-12-04","cited_by_count":22,"area":null},{"id":"2309.13701","title":"ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning","created":"2023-09-24","cited_by_count":15,"area":null},{"id":"2101.08153","title":"Shielding Atari Games with Bounded Prescience","created":"2021-01-20","cited_by_count":14,"area":null},{"id":"2208.14426","title":"Correct-by-Construction Runtime Enforcement in AI -- A Survey","created":"2022-08-30","cited_by_count":12,"area":null},{"id":"2207.13446","title":"Dynamic Shielding for Reinforcement Learning in Black-Box Environments","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2209.10341","title":"LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning","created":"2022-09-21","cited_by_count":11,"area":null},{"id":"2304.06281","title":"Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning","created":"2023-04-13","cited_by_count":11,"area":null},{"id":"2103.02363","title":"Reinforcement Learning with External Knowledge by using Logical Neural Networks","created":"2021-03-03","cited_by_count":10,"area":null},{"id":"2308.14424","title":"Shielded Reinforcement Learning for Hybrid Systems","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2201.03698","title":"Verified Probabilistic Policies for Deep Reinforcement Learning","created":"2022-01-10","cited_by_count":6,"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":"2303.14265","title":"Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2203.16275","title":"Reinforcement Learning Guided by Provable Normative Compliance","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2206.08881","title":"Logic-based Reward Shaping for Multi-Agent Reinforcement Learning","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2304.11593","title":"System III: Learning with Domain Knowledge for Safety Constraints","created":"2023-04-23","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":"2605.10888","title":"Shields to Guarantee Probabilistic Safety in MDPs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2312.11314","title":"Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2403.15916","title":"Multi-agent transformer-accelerated RL for satisfaction of STL specifications","created":"2024-03-23","cited_by_count":1,"area":null},{"id":"2304.03104","title":"Constrained Exploration in Reinforcement Learning with Optimality Preservation","created":"2023-04-05","cited_by_count":0,"area":null},{"id":"2311.00880","title":"SCPO: Safe Reinforcement Learning with Safety Critic Policy Optimization","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2606.00414","title":"Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.19632","title":"Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation","created":"2026-06-17","cited_by_count":0,"area":null}],"next_cursor":null}