{"total":19,"rows":[{"id":"2410.11671","title":"Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agents","created":"2024-10-15","cited_by_count":17,"area":"deeprl"},{"id":"2407.09645","title":"Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey","created":"2024-07-12","cited_by_count":16,"area":"deeprl"},{"id":"2409.13867","title":"MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety","created":"2024-09-20","cited_by_count":7,"area":"deeprl"},{"id":"2604.13192","title":"Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learning","created":"2026-04-14","cited_by_count":5,"area":"deeprl"},{"id":"2510.18082","title":"Provably Optimal Reinforcement Learning under Safety Filtering","created":"2025-10-20","cited_by_count":3,"area":"deeprl"},{"id":"2410.02898","title":"Deep Reinforcement Learning for Reach-Avoid-Stay Problems","created":"2024-10-03","cited_by_count":1,"area":"deeprl"},{"id":"2504.06386","title":"SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL","created":"2025-04-08","cited_by_count":1,"area":"deeprl"},{"id":"2511.21531","title":"Predictive Safety Shield for Dyna-Q Reinforcement Learning","created":"2025-11-26","cited_by_count":1,"area":"deeprl"},{"id":"2506.22894","title":"Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle Example","created":"2025-06-28","cited_by_count":0,"area":"deeprl"},{"id":"2512.01046","title":"Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids","created":"2025-11-30","cited_by_count":0,"area":"deeprl"},{"id":"2602.00636","title":"On the Equilibrium between Feasible Zone and Uncertain Model in Safe Exploration","created":"2026-01-31","cited_by_count":0,"area":"deeprl"},{"id":"2602.06525","title":"Progress Constraints for Reinforcement Learning in Behavior Trees","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2604.02727","title":"Data-Driven Synthesis of Probabilistic Controlled Invariant Sets for Linear MDPs","created":"2026-04-03","cited_by_count":0,"area":"deeprl"},{"id":"2605.05989","title":"Verifiable Model-Free Safety Filters via Reinforcement Learning","created":"2026-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2606.15311","title":"Hamilton-Jacobi Reachability-Based Safe Reinforcement Learning for Emergency Collision Avoidance","created":"2026-06-13","cited_by_count":0,"area":"deeprl"},{"id":"2606.31320","title":"Safe Online Learning via Smooth Safety-Structured Policy Composition","created":"2026-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2608.02433","title":"Foundations of Reinforcement Learning and Control:Connections and New Perspectives","created":"2026-08-03","cited_by_count":0,"area":"deeprl"},{"id":"2609.15988","title":"ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids","created":"2026-09-14","cited_by_count":0,"area":"deeprl"},{"id":"2609.27312","title":"Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning","created":"2026-09-23","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}