{"total":23,"rows":[{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2402.14528","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","created":"2024-02-22","cited_by_count":16,"area":"deeprl"},{"id":"2404.14064","title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","created":"2024-04-22","cited_by_count":8,"area":"deeprl"},{"id":"2405.19080","title":"OMPO: A Unified Framework for RL under Policy and Dynamics Shifts","created":"2024-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2411.08622","title":"Precision-Focused Reinforcement Learning Model for Robotic Object Pushing","created":"2024-11-13","cited_by_count":5,"area":"deeprl"},{"id":"2509.10423","title":"Mutual Information Tracks Policy Coherence in Reinforcement Learning","created":"2025-09-12","cited_by_count":4,"area":"deeprl"},{"id":"2402.03678","title":"Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents","created":"2024-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2511.14427","title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","created":"2025-11-18","cited_by_count":3,"area":"deeprl"},{"id":"2407.02503","title":"Optimizing Deep Reinforcement Learning for Adaptive Robotic Arm Control","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2406.04815","title":"Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning","created":"2024-06-07","cited_by_count":1,"area":"deeprl"},{"id":"2505.03356","title":"Effective Reinforcement Learning Control using Conservative Soft Actor-Critic","created":"2025-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2505.09737","title":"General Dynamic Goal Recognition using Goal-Conditioned and Meta Reinforcement Learning","created":"2025-05-14","cited_by_count":1,"area":"deeprl"},{"id":"2604.24729","title":"SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning","created":"2026-04-27","cited_by_count":1,"area":"deeprl"},{"id":"2503.12993","title":"Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach","created":"2025-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2504.11247","title":"Next-Future: Sample-Efficient Policy Learning for Robotic-Arm Tasks","created":"2025-04-15","cited_by_count":0,"area":"deeprl"},{"id":"2505.21536","title":"CiRL: Open-Source Environments for Reinforcement Learning in Circular Economy and Net Zero","created":"2025-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2506.13583","title":"Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processes","created":"2025-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2506.19785","title":"Learning Task Belief Similarity with Latent Dynamics for Meta-Reinforcement Learning","created":"2025-06-24","cited_by_count":0,"area":"deeprl"},{"id":"2509.25402","title":"Parallel Heuristic Search as Inference for Actor-Critic Reinforcement Learning Models","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2511.16158","title":"MagBotSim: Physics-Based Simulation and Reinforcement Learning Environments for Magnetic Robotics","created":"2025-11-20","cited_by_count":0,"area":"deeprl"},{"id":"2512.01047","title":"Automating the Refinement of Reinforcement Learning Specifications","created":"2025-11-30","cited_by_count":0,"area":"deeprl"},{"id":"2607.15935","title":"Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark","created":"2026-07-17","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}