{"total":94,"rows":[{"id":"2401.09750","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","created":"2024-01-18","cited_by_count":33,"area":"deeprl"},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32,"area":"deeprl"},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25,"area":"deeprl"},{"id":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17,"area":"deeprl"},{"id":"2402.05149","title":"FlowPG: Action-constrained Policy Gradient with Normalizing Flows","created":"2024-02-07","cited_by_count":16,"area":"deeprl"},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2410.20018","title":"GHIL-Glue: Hierarchical Control with Filtered Subgoal Images","created":"2024-10-26","cited_by_count":15,"area":"deeprl"},{"id":"2505.23527","title":"Normalizing Flows are Capable Models for Continuous Control","created":"2025-05-29","cited_by_count":14,"area":"deeprl"},{"id":"2404.07950","title":"Reinforcement Learning with Generalizable Gaussian Splatting","created":"2024-03-18","cited_by_count":13,"area":"deeprl"},{"id":"2406.17768","title":"EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data","created":"2024-06-25","cited_by_count":13,"area":"deeprl"},{"id":"2508.10316","title":"Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances","created":"2025-08-14","cited_by_count":12,"area":"deeprl"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","cited_by_count":10,"area":"deeprl"},{"id":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"area":"deeprl"},{"id":"2505.19785","title":"medDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Support","created":"2025-05-26","cited_by_count":9,"area":"deeprl"},{"id":"2507.02712","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","created":"2025-07-03","cited_by_count":9,"area":"deeprl"},{"id":"2602.01439","title":"TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse","created":"2026-02-01","cited_by_count":9,"area":"deeprl"},{"id":"2403.11062","title":"A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization","created":"2024-03-17","cited_by_count":7,"area":"deeprl"},{"id":"2412.02818","title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","created":"2024-12-03","cited_by_count":7,"area":"deeprl"},{"id":"2510.15382","title":"Towards Robust Zero-Shot Reinforcement Learning","created":"2025-10-17","cited_by_count":7,"area":"deeprl"},{"id":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","cited_by_count":6,"area":"deeprl"},{"id":"2406.02370","title":"Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning","created":"2024-06-04","cited_by_count":6,"area":"deeprl"},{"id":"2502.17322","title":"TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control","created":"2025-02-24","cited_by_count":6,"area":"deeprl"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2405.03113","title":"Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning","created":"2024-05-06","cited_by_count":5,"area":"deeprl"},{"id":"2406.03894","title":"Transductive Off-policy Proximal Policy Optimization","created":"2024-06-06","cited_by_count":5,"area":"deeprl"},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2402.13930","title":"Enhancing Reinforcement Learning Agents with Local Guides","created":"2024-02-21","cited_by_count":4,"area":"deeprl"},{"id":"2406.06037","title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","created":"2024-06-10","cited_by_count":4,"area":"deeprl"},{"id":"2505.08361","title":"Modeling Unseen Environments with Language-guided Composable Causal Components in Reinforcement Learning","created":"2025-05-13","cited_by_count":4,"area":"deeprl"},{"id":"2407.03995","title":"ROER: Regularized Optimal Experience Replay","created":"2024-07-04","cited_by_count":3,"area":"deeprl"},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2502.02834","title":"Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks","created":"2025-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","created":"2025-06-14","cited_by_count":3,"area":"deeprl"},{"id":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2401.08959","title":"Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback","created":"2024-01-17","cited_by_count":2,"area":"deeprl"},{"id":"2402.11317","title":"Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics","created":"2024-02-17","cited_by_count":2,"area":"deeprl"},{"id":"2412.13106","title":"Active Reinforcement Learning Strategies for Offline Policy Improvement","created":"2024-12-17","cited_by_count":2,"area":"deeprl"},{"id":"2502.10431","title":"Leveraging Constraint Violation Signals For Action-Constrained Reinforcement Learning","created":"2025-02-08","cited_by_count":2,"area":"deeprl"},{"id":"2505.11862","title":"Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement Learning","created":"2025-05-17","cited_by_count":2,"area":"deeprl"},{"id":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2506.13345","title":"Learning to Explore in Diverse Reward Settings via Temporal-Difference-Error Maximization","created":"2025-06-16","cited_by_count":2,"area":"deeprl"},{"id":"2511.10843","title":"Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning","created":"2025-11-13","cited_by_count":2,"area":"deeprl"},{"id":"2512.21527","title":"Generative Actor Critic","created":"2025-12-25","cited_by_count":2,"area":"deeprl"},{"id":"2607.27203","title":"Do You Really Need to Pretrain Q-Functions for Online RL Fine-Tuning?","created":"2026-07-29","cited_by_count":2,"area":"deeprl"},{"id":"2402.13654","title":"Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark","created":"2024-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2404.16159","title":"AFU: Actor-Free critic Updates in off-policy RL for continuous control","created":"2024-04-24","cited_by_count":1,"area":"deeprl"},{"id":"2506.12095","title":"DoublyAware: Dual Planning and Policy Awareness for Temporal Difference Learning in Humanoid Locomotion","created":"2025-06-12","cited_by_count":1,"area":"deeprl"},{"id":"2509.04069","title":"Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning","created":"2025-09-04","cited_by_count":1,"area":"deeprl"},{"id":"2510.07919","title":"GRADE: Personalized Multi-Task Fusion via Group-relative Reinforcement Learning with Adaptive Dirichlet Exploration","created":"2025-10-09","cited_by_count":1,"area":"deeprl"},{"id":"2512.00303","title":"Gradient Inversion in Federated Reinforcement Learning","created":"2025-11-29","cited_by_count":1,"area":"deeprl"},{"id":"2603.03955","title":"GIPO: Gaussian Importance Sampling Policy Optimization","created":"2026-03-04","cited_by_count":1,"area":"deeprl"},{"id":"2605.05863","title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","created":"2026-05-07","cited_by_count":1,"area":"deeprl"},{"id":"2605.21214","title":"Behavior-Consistent Deep Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2606.29820","title":"Dual-Flow Reinforcement Learning with State-Aware Exploration","created":"2026-06-29","cited_by_count":1,"area":"deeprl"},{"id":"2608.15088","title":"Max-Q Selective Imitation for Human-in-the-Loop Online Robot Learning","created":"2026-08-15","cited_by_count":1,"area":"deeprl"},{"id":"2402.05950","title":"SQT -- std $Q$-target","created":"2024-02-03","cited_by_count":0,"area":"deeprl"},{"id":"2402.09200","title":"Discovering Command and Control (C2) Channels on Tor and Public Networks Using Reinforcement Learning","created":"2024-02-14","cited_by_count":0,"area":"deeprl"},{"id":"2409.07341","title":"Online Decision MetaMorphFormer: A Casual Transformer-Based Reinforcement Learning Framework of Universal Embodied Intelligence","created":"2024-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2409.11678","title":"EnhancedRL: An Enhanced-State Reinforcement Learning Algorithm for Multi-Task Fusion in Recommender Systems","created":"2024-09-18","cited_by_count":0,"area":"deeprl"},{"id":"2410.12598","title":"Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach","created":"2024-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2410.23840","title":"Deterministic Exploration via Stationary Bellman Error Maximization","created":"2024-10-31","cited_by_count":0,"area":"deeprl"},{"id":"2412.10381","title":"Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in Feed","created":"2024-11-28","cited_by_count":0,"area":"deeprl"},{"id":"2504.21326","title":"Q-function Decomposition with Intervention Semantics with Factored Action Spaces","created":"2025-04-30","cited_by_count":0,"area":"deeprl"},{"id":"2505.12109","title":"SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces","created":"2025-05-17","cited_by_count":0,"area":"deeprl"},{"id":"2509.19771","title":"Frictional Q-Learning","created":"2025-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2509.22310","title":"Adaptive Policy Backbone via Shared Network","created":"2025-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2510.22859","title":"Guardian: Decoupling Exploration from Safety in Reinforcement Learning","created":"2025-10-26","cited_by_count":0,"area":"deeprl"},{"id":"2510.24432","title":"Fill in the Blanks: Accelerating Q-Learning with a Handful of Demonstrations in Sparse Reward Settings","created":"2025-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2512.05320","title":"Enhancing Deep Deterministic Policy Gradients on Continuous Control Tasks with Decoupled Prioritized Experience Replay","created":"2025-12-04","cited_by_count":0,"area":"deeprl"},{"id":"2512.20220","title":"Generalisation in Multitask Fitted Q-Iteration and Offline Q-learning","created":"2025-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2512.24955","title":"MSACL: Multi-Step Actor-Critic Learning with Lyapunov Certificates for Exponentially Stabilizing Control","created":"2025-12-31","cited_by_count":0,"area":"deeprl"},{"id":"2601.02754","title":"Q-Regularized Generative Auto-Bidding: From Suboptimal Trajectories to Optimal Policies","created":"2026-01-06","cited_by_count":0,"area":"deeprl"},{"id":"2601.20193","title":"Meta-Cognitive Reinforcement Learning with Self-Doubt and Recovery","created":"2026-01-28","cited_by_count":0,"area":"deeprl"},{"id":"2602.09726","title":"ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm","created":"2026-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2602.19298","title":"ALPACA: A Reinforcement Learning Environment for Medication Repurposing and Treatment Optimization in Alzheimer's Disease","created":"2026-02-22","cited_by_count":0,"area":"deeprl"},{"id":"2602.24037","title":"Portfolio Reinforcement Learning with Scenario-Context Rollout","created":"2026-02-27","cited_by_count":0,"area":"deeprl"},{"id":"2603.01553","title":"State-Action Inpainting Diffuser for Continuous Control with Delay","created":"2026-03-02","cited_by_count":0,"area":"deeprl"},{"id":"2603.03820","title":"Fairness Begins with State: Purifying Latent Preferences for Hierarchical Reinforcement Learning in Interactive Recommendation","created":"2026-03-04","cited_by_count":0,"area":"deeprl"},{"id":"2604.25379","title":"Safe-Support Q-Learning: Learning without Unsafe Exploration","created":"2026-04-28","cited_by_count":0,"area":"deeprl"},{"id":"2605.25114","title":"Counterfactually Safe Reinforcement Learning","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.31691","title":"FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion","created":"2026-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2607.21302","title":"Expert Behavior Prior Reinforcement Learning","created":"2026-07-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.28916","title":"Gated Q-learning: Add Off-Policy Bias to Taste","created":"2026-07-31","cited_by_count":0,"area":"deeprl"},{"id":"2608.02034","title":"Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement Learning","created":"2026-08-03","cited_by_count":0,"area":"deeprl"},{"id":"2609.20098","title":"CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning","created":"2026-09-17","cited_by_count":0,"area":"deeprl"},{"id":"2609.23374","title":"The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions","created":"2026-09-20","cited_by_count":0,"area":"deeprl"},{"id":"2609.28581","title":"Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning","created":"2026-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2609.39911","title":"Patient-Centered Treatment Planning for Chronic Multimorbidity: A Hierarchical Reinforcement Learning Framework for Preference Modeling","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.04754","title":"FoSeRL: Formal Sequential Robustness Certification for Reinforcement Learning Policies","created":"2026-10-03","cited_by_count":0,"area":"deeprl"},{"id":"2610.18839","title":"Fast Rates for Offline Q-Learning with KL Regularization","created":"2026-10-13","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}