{"total":25,"rows":[{"id":"2405.00662","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","created":"2024-05-01","cited_by_count":27,"area":"deeprl"},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2402.02868","title":"Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem","created":"2024-02-05","cited_by_count":23,"area":"deeprl"},{"id":"2403.06323","title":"A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents","created":"2024-03-10","cited_by_count":16,"area":"deeprl"},{"id":"2506.13672","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","created":"2025-06-16","cited_by_count":6,"area":"deeprl"},{"id":"2401.09286","title":"Deployable Reinforcement Learning with Variable Control Rate","created":"2024-01-17","cited_by_count":5,"area":"deeprl"},{"id":"2403.03552","title":"Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning","created":"2024-03-06","cited_by_count":5,"area":"deeprl"},{"id":"2410.01431","title":"Scalable Reinforcement Learning-based Neural Architecture Search","created":"2024-10-02","cited_by_count":5,"area":"deeprl"},{"id":"2402.14961","title":"Reinforcement Learning with Elastic Time Steps","created":"2024-02-22","cited_by_count":3,"area":"deeprl"},{"id":"2406.01641","title":"Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents","created":"2024-06-03","cited_by_count":3,"area":"deeprl"},{"id":"2407.03311","title":"Efficient Imitation Without Demonstrations via Value-Penalized Auxiliary Control from Examples","created":"2024-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2512.06252","title":"Learning Without Time-Based Embodiment Resets in Soft-Actor Critic","created":"2025-12-06","cited_by_count":1,"area":"deeprl"},{"id":"2602.04131","title":"Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting","created":"2026-02-04","cited_by_count":1,"area":"deeprl"},{"id":"2403.00673","title":"Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiency","created":"2024-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2410.06317","title":"Learning in complex action spaces without policy gradients","created":"2024-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2412.01420","title":"Task Adaptation of Reinforcement Learning-based NAS Agents through Transfer Learning","created":"2024-12-02","cited_by_count":0,"area":"deeprl"},{"id":"2505.07832","title":"A General Approach of Automated Environment Design for Learning the Optimal Power Flow","created":"2025-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2506.19353","title":"Partially Observable Residual Reinforcement Learning for PV-Inverter-Based Voltage Control in Distribution Grids","created":"2025-06-24","cited_by_count":0,"area":"deeprl"},{"id":"2509.23556","title":"Zero-shot Whole-Body Manipulation with a Large-Scale Soft Robotic Torso via Guided Reinforcement Learning","created":"2025-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2603.16842","title":"Stochastic Resetting Accelerates Reinforcement Learning Beyond Random Search","created":"2026-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2604.19033","title":"Intentional Updates for Streaming Reinforcement Learning","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2605.19166","title":"A Heuristic Approach for Performance Tuning in RL-based Quadrotor Control via Reward Design and Termination Conditions","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2606.04574","title":"Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning","created":"2026-06-03","cited_by_count":0,"area":"deeprl"},{"id":"2609.05569","title":"Information-Guided Safe Reinforcement Learning for Autonomous Gas Source Localization using sUAS","created":"2026-09-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.05446","title":"Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}