{"total":129,"rows":[{"id":"2510.14830","title":"RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning","created":"2025-10-16","cited_by_count":59,"area":"deeprl"},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2404.12308","title":"ASID: Active Exploration for System Identification in Robotic Manipulation","created":"2024-04-18","cited_by_count":28,"area":"deeprl"},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2502.02133","title":"Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification","created":"2025-02-04","cited_by_count":26,"area":"deeprl"},{"id":"2410.09486","title":"ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning","created":"2024-10-12","cited_by_count":23,"area":"deeprl"},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2405.19014","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","created":"2024-05-29","cited_by_count":18,"area":"deeprl"},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"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":"2410.09163","title":"Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models","created":"2024-10-11","cited_by_count":16,"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":"2402.08991","title":"Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption","created":"2024-02-14","cited_by_count":12,"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":"2401.12497","title":"Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning","created":"2024-01-23","cited_by_count":11,"area":"deeprl"},{"id":"2408.08994","title":"Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds","created":"2024-08-16","cited_by_count":11,"area":"deeprl"},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2406.01163","title":"When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL","created":"2024-06-03","cited_by_count":9,"area":"deeprl"},{"id":"2406.15131","title":"KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty","created":"2024-06-21","cited_by_count":9,"area":"deeprl"},{"id":"2408.08706","title":"Efficient Multi-Policy Evaluation for Reinforcement Learning","created":"2024-08-16","cited_by_count":9,"area":"deeprl"},{"id":"2404.03037","title":"Model-based Reinforcement Learning for Parameterized Action Spaces","created":"2024-04-03","cited_by_count":8,"area":"deeprl"},{"id":"2406.16707","title":"Probabilistic Subgoal Representations for Hierarchical Reinforcement learning","created":"2024-06-24","cited_by_count":8,"area":"deeprl"},{"id":"2410.02226","title":"Doubly Optimal Policy Evaluation for Reinforcement Learning","created":"2024-10-03","cited_by_count":8,"area":"deeprl"},{"id":"2510.07257","title":"Test-Time Graph Search for Goal-Conditioned Reinforcement Learning","created":"2025-10-08","cited_by_count":8,"area":"deeprl"},{"id":"2408.17380","title":"Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control","created":"2024-08-30","cited_by_count":7,"area":"deeprl"},{"id":"2411.10175","title":"The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning","created":"2024-11-15","cited_by_count":7,"area":"deeprl"},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","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":"2410.04553","title":"Bisimulation metric for Model Predictive Control","created":"2024-10-06","cited_by_count":6,"area":"deeprl"},{"id":"2410.05655","title":"Efficient Policy Evaluation with Safety Constraint for Reinforcement Learning","created":"2024-10-08","cited_by_count":6,"area":"deeprl"},{"id":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","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":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","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":"2402.05476","title":"Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization","created":"2024-02-08","cited_by_count":5,"area":"deeprl"},{"id":"2407.12195","title":"A Safe and Data-efficient Model-based Reinforcement Learning System for HVAC Control","created":"2024-07-16","cited_by_count":5,"area":"deeprl"},{"id":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"id":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"id":"2604.25416","title":"Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Dynamics Models","created":"2026-04-28","cited_by_count":5,"area":"deeprl"},{"id":"2401.07369","title":"CoVO-MPC: Theoretical Analysis of Sampling-based MPC and Optimal Covariance Design","created":"2024-01-14","cited_by_count":4,"area":"deeprl"},{"id":"2406.01175","title":"NeoRL: Efficient Exploration for Nonepisodic RL","created":"2024-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2407.18841","title":"QT-TDM: Planning With Transformer Dynamics Model and Autoregressive Q-Learning","created":"2024-07-26","cited_by_count":4,"area":"deeprl"},{"id":"2503.17678","title":"Computationally and Sample Efficient Safe Reinforcement Learning Using Adaptive Conformal Prediction","created":"2025-03-22","cited_by_count":4,"area":"deeprl"},{"id":"2403.12210","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","created":"2024-03-18","cited_by_count":3,"area":"deeprl"},{"id":"2404.10942","title":"What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning","created":"2024-04-16","cited_by_count":3,"area":"deeprl"},{"id":"2407.21338","title":"Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Tasks","created":"2024-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2409.19617","title":"LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World","created":"2024-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2410.04988","title":"Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling","created":"2024-10-07","cited_by_count":3,"area":"deeprl"},{"id":"2503.20139","title":"Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning","created":"2025-03-26","cited_by_count":3,"area":"deeprl"},{"id":"2504.02543","title":"Optimal Control of Probabilistic Dynamics Models via Mean Hamiltonian Minimization","created":"2025-04-03","cited_by_count":3,"area":"deeprl"},{"id":"2505.23003","title":"Hybrid Cross-domain Robust Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2510.24482","title":"Sample-efficient and Scalable Exploration in Continuous-Time RL","created":"2025-10-28","cited_by_count":3,"area":"deeprl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2405.16184","title":"Safe Deep Model-Based Reinforcement Learning with Lyapunov Functions","created":"2024-05-25","cited_by_count":2,"area":"deeprl"},{"id":"2406.07877","title":"Hierarchical Reinforcement Learning for Swarm Confrontation with High Uncertainty","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2407.02217","title":"Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning","created":"2024-07-02","cited_by_count":2,"area":"deeprl"},{"id":"2409.09990","title":"SHIRE: Enhancing Sample Efficiency using Human Intuition in REinforcement Learning","created":"2024-09-16","cited_by_count":2,"area":"deeprl"},{"id":"2410.12160","title":"When to Trust Your Data: Enhancing Dyna-Style Model-Based Reinforcement Learning With Data Filter","created":"2024-10-16","cited_by_count":2,"area":"deeprl"},{"id":"2411.04098","title":"Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems","created":"2024-11-06","cited_by_count":2,"area":"deeprl"},{"id":"2412.00086","title":"Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning","created":"2024-11-27","cited_by_count":2,"area":"deeprl"},{"id":"2412.11743","title":"Generalized Bayesian deep reinforcement learning","created":"2024-12-16","cited_by_count":2,"area":"deeprl"},{"id":"2502.05001","title":"A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach","created":"2025-02-07","cited_by_count":2,"area":"deeprl"},{"id":"2505.22772","title":"Calibrated Value-Aware Model Learning with Probabilistic Environment Models","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2506.04399","title":"Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning","created":"2025-06-04","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":"2509.06296","title":"Learning to Walk With Less: A Dyna-Style Approach to Quadrupedal Locomotion","created":"2025-09-08","cited_by_count":2,"area":"deeprl"},{"id":"2604.10974","title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","created":"2026-04-13","cited_by_count":2,"area":"deeprl"},{"id":"2605.16692","title":"EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control","created":"2026-05-15","cited_by_count":2,"area":"deeprl"},{"id":"2402.03146","title":"A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning","created":"2024-02-05","cited_by_count":1,"area":"deeprl"},{"id":"2402.05307","title":"Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2403.14860","title":"Robust Model Based Reinforcement Learning Using $\\mathcal{L}_1$ Adaptive Control","created":"2024-03-21","cited_by_count":1,"area":"deeprl"},{"id":"2404.19462","title":"Continual Model-based Reinforcement Learning for Data Efficient Wireless Network Optimisation","created":"2024-04-30","cited_by_count":1,"area":"deeprl"},{"id":"2410.13490","title":"Novelty-based Sample Reuse for Continuous Robotics Control","created":"2024-10-17","cited_by_count":1,"area":"deeprl"},{"id":"2411.01396","title":"Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning","created":"2024-11-03","cited_by_count":1,"area":"deeprl"},{"id":"2503.15629","title":"Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning","created":"2025-03-19","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":"2506.12735","title":"Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space Modeling","created":"2025-06-15","cited_by_count":1,"area":"deeprl"},{"id":"2512.15439","title":"Double Horizon Model-Based Policy Optimization","created":"2025-12-17","cited_by_count":1,"area":"deeprl"},{"id":"2603.23245","title":"Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning","created":"2026-03-24","cited_by_count":1,"area":"deeprl"},{"id":"2604.02260","title":"Model-Based Reinforcement Learning for Control under Time-Varying Dynamics","created":"2026-04-02","cited_by_count":1,"area":"deeprl"},{"id":"2605.04709","title":"ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC","created":"2026-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2605.08946","title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","created":"2026-05-09","cited_by_count":1,"area":"deeprl"},{"id":"2607.12523","title":"OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning","created":"2026-07-14","cited_by_count":1,"area":"deeprl"},{"id":"2608.19375","title":"Learning the Right Abstraction: Neural Reduced Dynamics for Complex Robot Control","created":"2026-08-19","cited_by_count":1,"area":"deeprl"},{"id":"2402.11877","title":"Learning the Model While Learning Q: Finite-Time Sample Complexity of Online SyncMBQ","created":"2024-02-19","cited_by_count":0,"area":"deeprl"},{"id":"2403.01529","title":"Deep Incremental Model Informed Reinforcement Learning for Continuous Robotic Control","created":"2024-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2403.07979","title":"Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning","created":"2024-03-12","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":"2405.02598","title":"UDUC: An Uncertainty-driven Approach for Learning-based Robust Control","created":"2024-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2406.19561","title":"Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning","created":"2024-06-27","cited_by_count":0,"area":"deeprl"},{"id":"2410.12250","title":"Dual Action Policy for Robust Sim-to-Real Reinforcement Learning","created":"2024-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2412.20537","title":"Diminishing Return of Value Expansion Methods","created":"2024-12-29","cited_by_count":0,"area":"deeprl"},{"id":"2501.02205","title":"Digital Twin Calibration with Model-Based Reinforcement Learning","created":"2025-01-04","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":"2503.13842","title":"Counterfactual experience augmented off-policy reinforcement learning","created":"2025-03-18","cited_by_count":0,"area":"deeprl"},{"id":"2504.21585","title":"Multi-Goal Dexterous Hand Manipulation using Probabilistic Model-based Reinforcement Learning","created":"2025-04-30","cited_by_count":0,"area":"deeprl"},{"id":"2505.15754","title":"Improving planning and MBRL with temporally-extended actions","created":"2025-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2506.02205","title":"Bregman Centroid Guided Cross-Entropy Method","created":"2025-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2510.01457","title":"A Forensic Analysis of Synthetic Data in RL: Diagnosing and Solving Algorithmic Failures in Model-Based Policy Optimization","created":"2025-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}