{"total":116,"rows":[{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2401.09561","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","created":"2024-01-17","cited_by_count":44,"area":"deeprl"},{"id":"2401.09750","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","created":"2024-01-18","cited_by_count":33,"area":"deeprl"},{"id":"2501.17827","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","created":"2025-01-29","cited_by_count":17,"area":"deeprl"},{"id":"2401.14758","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","created":"2024-01-26","cited_by_count":14,"area":"deeprl"},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2406.12241","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","created":"2024-06-18","cited_by_count":12,"area":"deeprl"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2603.15789","title":"Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learning","created":"2026-03-16","cited_by_count":10,"area":"deeprl"},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2507.05477","title":"Epistemically-guided forward-backward exploration","created":"2025-07-07","cited_by_count":8,"area":"deeprl"},{"id":"2401.08850","title":"REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes","created":"2024-01-16","cited_by_count":6,"area":"deeprl"},{"id":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","cited_by_count":6,"area":"deeprl"},{"id":"2403.02107","title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning","created":"2024-03-04","cited_by_count":6,"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":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2506.09270","title":"Uncertainty Prioritized Experience Replay","created":"2025-06-10","cited_by_count":6,"area":"deeprl"},{"id":"2406.19768","title":"Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors","created":"2024-06-28","cited_by_count":5,"area":"deeprl"},{"id":"2407.00801","title":"Model-Free Active Exploration in Reinforcement Learning","created":"2024-06-30","cited_by_count":5,"area":"deeprl"},{"id":"2502.20265","title":"On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+($\\lambda$,$\\lambda$))-GA","created":"2025-02-27","cited_by_count":5,"area":"deeprl"},{"id":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"id":"2402.03055","title":"Deep Exploration with PAC-Bayes","created":"2024-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2402.08022","title":"Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks","created":"2024-02-12","cited_by_count":4,"area":"deeprl"},{"id":"2403.08152","title":"Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning","created":"2024-03-13","cited_by_count":4,"area":"deeprl"},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2502.20341","title":"Safety Representations for Safer Policy Learning","created":"2025-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2506.04398","title":"Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2507.13181","title":"Spectral Bellman Method: Unifying Representation and Exploration in RL","created":"2025-07-17","cited_by_count":4,"area":"deeprl"},{"id":"2602.08690","title":"SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity","created":"2026-02-09","cited_by_count":4,"area":"deeprl"},{"id":"2402.05439","title":"Learning Uncertainty-Aware Temporally-Extended Actions","created":"2024-02-08","cited_by_count":3,"area":"deeprl"},{"id":"2402.07107","title":"Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning","created":"2024-02-11","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":"2410.11833","title":"Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions","created":"2024-10-15","cited_by_count":3,"area":"deeprl"},{"id":"2501.00913","title":"$\\beta$-DQN: Improving Deep Q-Learning By Evolving the Behavior","created":"2025-01-01","cited_by_count":3,"area":"deeprl"},{"id":"2510.25529","title":"Off-policy Reinforcement Learning with Model-based Exploration Augmentation","created":"2025-10-29","cited_by_count":3,"area":"deeprl"},{"id":"2602.08557","title":"Combined Constrained Sampling and Reinforcement Learning for Robotic Manipulation","created":"2026-02-09","cited_by_count":3,"area":"deeprl"},{"id":"2403.13178","title":"Fast Value Tracking for Deep Reinforcement Learning","created":"2024-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2408.08446","title":"Lifelong Reinforcement Learning via Neuromodulation","created":"2024-08-15","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":"2503.05696","title":"A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation","created":"2025-03-07","cited_by_count":2,"area":"deeprl"},{"id":"2506.24005","title":"Provably Efficient and Agile Randomized Q-Learning","created":"2025-06-30","cited_by_count":2,"area":"deeprl"},{"id":"2507.02639","title":"On Efficient Bayesian Exploration in Model-Based Reinforcement Learning","created":"2025-07-03","cited_by_count":2,"area":"deeprl"},{"id":"2510.14503","title":"Learning to Undo: Rollback-Augmented Reinforcement Learning with Reversibility Signals","created":"2025-10-16","cited_by_count":2,"area":"deeprl"},{"id":"2603.18396","title":"RE-SAC: Disentangling aleatoric and epistemic risks in bus fleet control: A stable and robust ensemble DRL approach","created":"2026-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2606.10228","title":"SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration","created":"2026-06-08","cited_by_count":2,"area":"deeprl"},{"id":"2405.08638","title":"vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement","created":"2024-05-14","cited_by_count":1,"area":"deeprl"},{"id":"2409.05433","title":"State-Novelty Guided Action Persistence in Deep Reinforcement Learning","created":"2024-09-09","cited_by_count":1,"area":"deeprl"},{"id":"2501.15129","title":"EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning","created":"2025-01-25","cited_by_count":1,"area":"deeprl"},{"id":"2505.11044","title":"Exploration by Random Distribution Distillation","created":"2025-05-16","cited_by_count":1,"area":"deeprl"},{"id":"2505.16167","title":"Tactile-based Reinforcement Learning for Adaptive Grasping under Observation Uncertainties","created":"2025-05-22","cited_by_count":1,"area":"deeprl"},{"id":"2506.00917","title":"Q-learning with Posterior Sampling","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2507.00275","title":"Deep Double Q-learning","created":"2025-06-30","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2510.19531","title":"The Confusing Instance Principle for Online Linear Quadratic Control","created":"2025-10-22","cited_by_count":1,"area":"deeprl"},{"id":"2512.03805","title":"Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+($\\lambda$,$\\lambda$))-GA","created":"2025-12-03","cited_by_count":1,"area":"deeprl"},{"id":"2601.03015","title":"In-Context Reinforcement Learning through Bayesian Fusion of Context and Value Prior","created":"2026-01-06","cited_by_count":1,"area":"deeprl"},{"id":"2602.12375","title":"Value Bonuses using Ensemble Errors for Exploration in Reinforcement Learning","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2603.22273","title":"Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration","created":"2026-03-23","cited_by_count":1,"area":"deeprl"},{"id":"2604.21863","title":"Replay-buffer engineering for noise-aware quantum circuit optimization","created":"2026-04-23","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":"2606.05888","title":"Retry Policy Gradients in Continuous Action Spaces","created":"2026-06-04","cited_by_count":1,"area":"deeprl"},{"id":"2606.23640","title":"Learning Process Rewards via Success Visitation Matching for Efficient RL","created":"2026-06-22","cited_by_count":1,"area":"deeprl"},{"id":"2403.17542","title":"VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts","created":"2024-03-26","cited_by_count":0,"area":"deeprl"},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2404.01867","title":"Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation","created":"2024-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2404.12999","title":"Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning","created":"2024-04-19","cited_by_count":0,"area":"deeprl"},{"id":"2408.02295","title":"Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning","created":"2024-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2408.14009","title":"Optimizing TD3 for 7-DOF Robotic Arm Grasping: Overcoming Suboptimality with Exploration-Enhanced Contrastive Learning","created":"2024-08-26","cited_by_count":0,"area":"deeprl"},{"id":"2410.03119","title":"Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems","created":"2024-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2501.09611","title":"EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning","created":"2025-01-16","cited_by_count":0,"area":"deeprl"},{"id":"2501.11818","title":"Group-Agent Reinforcement Learning with Heterogeneous Agents","created":"2025-01-21","cited_by_count":0,"area":"deeprl"},{"id":"2501.13394","title":"Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration","created":"2025-01-23","cited_by_count":0,"area":"deeprl"},{"id":"2502.17518","title":"Ensemble RL through Classifier Models: Enhancing Risk-Return Trade-offs in Trading Strategies","created":"2025-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2503.00227","title":"The Learning Approach to Games","created":"2025-02-28","cited_by_count":0,"area":"deeprl"},{"id":"2505.08453","title":"Parameter Estimation using Reinforcement Learning Causal Curiosity: Limits and Challenges","created":"2025-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2506.21127","title":"Meta Policy Switching for Secure UAV Deconfliction in Adversarial Airspace","created":"2025-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2506.22566","title":"Exploration Behavior of Untrained Policies","created":"2025-06-27","cited_by_count":0,"area":"deeprl"},{"id":"2507.05465","title":"2048: Reinforcement Learning in a Delayed Reward Environment","created":"2025-07-07","cited_by_count":0,"area":"deeprl"},{"id":"2507.11482","title":"Illuminating the Three Dogmas of Reinforcement Learning under Evolutionary Light","created":"2025-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2508.21488","title":"Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning","created":"2025-08-29","cited_by_count":0,"area":"deeprl"},{"id":"2509.04815","title":"An Arbitration Control for an Ensemble of Diversified DQN variants in Continual Reinforcement Learning","created":"2025-09-05","cited_by_count":0,"area":"deeprl"},{"id":"2509.15981","title":"Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations","created":"2025-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2509.22964","title":"Functional Critics Are Essential for Actor-Critic: From Off-Policy Stability to Efficient Exploration","created":"2025-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2511.02969","title":"Value of Information-Enhanced Exploration in Bootstrapped DQN","created":"2025-11-04","cited_by_count":0,"area":"deeprl"},{"id":"2512.10492","title":"UACER: An Uncertainty-Adaptive Critic Ensemble Framework for Robust Adversarial Reinforcement Learning","created":"2025-12-11","cited_by_count":0,"area":"deeprl"},{"id":"2512.17034","title":"GB-DQN: Gradient Boosted DQN Models for Non-stationary Reinforcement Learning","created":"2025-12-18","cited_by_count":0,"area":"deeprl"},{"id":"2512.17929","title":"Reinforcement Learning for Monetary Policy Under Macroeconomic Uncertainty: Analyzing Tabular and Function Approximation Methods","created":"2025-12-09","cited_by_count":0,"area":"deeprl"},{"id":"2512.22910","title":"Sat-EnQ: Satisficing Ensembles of Weak Q-Learners for Reliable and Compute-Efficient Reinforcement Learning","created":"2025-12-28","cited_by_count":0,"area":"deeprl"},{"id":"2601.00007","title":"Yahtzee: Reinforcement Learning Techniques for Stochastic Combinatorial Games","created":"2025-12-18","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":"2601.22339","title":"Quantum-Inspired Reinforcement Learning for Secure and Sustainable AIoT-Driven Supply Chain Systems","created":"2026-01-29","cited_by_count":0,"area":"deeprl"},{"id":"2603.01452","title":"Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning","created":"2026-03-02","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":"2603.17947","title":"Unified Policy Value Decomposition for Rapid Adaptation","created":"2026-03-18","cited_by_count":0,"area":"deeprl"},{"id":"2604.11914","title":"Self-Monitoring Benefits from Structural Integration: Lessons from Metacognition in Continuous-Time Multi-Timescale Agents","created":"2026-04-13","cited_by_count":0,"area":"deeprl"},{"id":"2604.13414","title":"Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence","created":"2026-04-15","cited_by_count":0,"area":"deeprl"},{"id":"2604.27411","title":"Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift","created":"2026-04-30","cited_by_count":0,"area":"deeprl"},{"id":"2605.05856","title":"Gradient-Momentum Coupling: A Parameter-Space Proxy for Learning Progress","created":"2026-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2605.09109","title":"When (and How) to Trust the Expert: Diagnosing Query-Time Expert-Guided Reinforcement Learning","created":"2026-05-09","cited_by_count":0,"area":"deeprl"},{"id":"2605.26155","title":"When Does Adaptive Guidance Help? Belief-Aware Privileged Distillation for Autonomous Driving Under Partial Observability","created":"2026-05-24","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}