{"total":168,"rows":[{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644,"area":"wm"},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397,"area":"wm"},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125,"area":"offlinerl"},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114,"area":"driving"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104,"area":null},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86,"area":null},{"id":"2401.02644","title":"Simple Hierarchical Planning with Diffusion","created":"2024-01-05","cited_by_count":73,"area":"diffusion"},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2110.04135","title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning","created":"2021-10-08","cited_by_count":50,"area":"offlinerl"},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"area":null},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42,"area":"offlinerl"},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2505.00779","title":"Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures","created":"2025-05-01","cited_by_count":33,"area":"wm"},{"id":"2211.07357","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","created":"2022-11-11","cited_by_count":29,"area":null},{"id":"2306.15713","title":"Rethinking Closed-loop Training for Autonomous Driving","created":"2023-06-27","cited_by_count":29,"area":"driving"},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27,"area":null},{"id":"2105.06022","title":"Principled Exploration via Optimistic Bootstrapping and Backward Induction","created":"2021-05-13","cited_by_count":26,"area":null},{"id":"2410.20750","title":"ODRL: A Benchmark for Off-Dynamics Reinforcement Learning","created":"2024-10-28","cited_by_count":25,"area":"deeprl"},{"id":"2108.01843","title":"Model-Based Opponent Modeling","created":"2021-08-04","cited_by_count":22,"area":null},{"id":"2109.14311","title":"Learning Dynamics Models for Model Predictive Agents","created":"2021-09-29","cited_by_count":22,"area":null},{"id":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21,"area":"offlinerl"},{"id":"2108.11811","title":"When should agents explore?","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2302.01244","title":"Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function","created":"2023-02-02","cited_by_count":19,"area":null},{"id":"2105.04682","title":"Value Iteration in Continuous Actions, States and Time","created":"2021-05-10","cited_by_count":18,"area":null},{"id":"2107.01825","title":"Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation","created":"2021-07-05","cited_by_count":18,"area":null},{"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":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2211.02222","title":"The Benefits of Model-Based Generalization in Reinforcement Learning","created":"2022-11-04","cited_by_count":17,"area":null},{"id":"2301.08502","title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning","created":"2023-01-20","cited_by_count":17,"area":null},{"id":"2210.03802","title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization","created":"2022-10-07","cited_by_count":16,"area":"offlinerl"},{"id":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16,"area":null},{"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":"2107.00306","title":"MHER: Model-based Hindsight Experience Replay","created":"2021-07-01","cited_by_count":15,"area":null},{"id":"2112.04643","title":"Autoregressive Quantile Flows for Predictive Uncertainty Estimation","created":"2021-12-09","cited_by_count":15,"area":null},{"id":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15,"area":"offlinerl"},{"id":"2302.12526","title":"Model-Based Uncertainty in Value Functions","created":"2023-02-24","cited_by_count":15,"area":null},{"id":"2210.08349","title":"When to Update Your Model: Constrained Model-based Reinforcement Learning","created":"2022-10-15","cited_by_count":14,"area":null},{"id":"2310.07220","title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL","created":"2023-10-11","cited_by_count":14,"area":null},{"id":"2401.03306","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","created":"2024-01-06","cited_by_count":14,"area":"offlinerl"},{"id":"2105.06350","title":"MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks","created":"2021-05-13","cited_by_count":13,"area":null},{"id":"2111.08550","title":"On Effective Scheduling of Model-based Reinforcement Learning","created":"2021-11-16","cited_by_count":13,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2107.06434","title":"Centralized Model and Exploration Policy for Multi-Agent RL","created":"2021-07-14","cited_by_count":12,"area":null},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2307.02770","title":"Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback","created":"2023-07-06","cited_by_count":12,"area":"diffusion"},{"id":"2110.04422","title":"Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation","created":"2021-10-09","cited_by_count":11,"area":null},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"area":null},{"id":"2405.17031","title":"Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":10,"area":"offlinerl"},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2212.04280","title":"Model-based trajectory stitching for improved behavioural cloning and its applications","created":"2022-12-08","cited_by_count":9,"area":"offlinerl"},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2102.11513","title":"Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model","created":"2021-02-23","cited_by_count":8,"area":null},{"id":"2110.02414","title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks","created":"2021-10-05","cited_by_count":8,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2101.09650","title":"GST: Group-Sparse Training for Accelerating Deep Reinforcement Learning","created":"2021-01-24","cited_by_count":7,"area":null},{"id":"2305.12240","title":"Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics","created":"2023-05-20","cited_by_count":7,"area":null},{"id":"2309.09982","title":"Introspective Deep Metric Learning","created":"2023-09-11","cited_by_count":7,"area":null},{"id":"2406.00153","title":"$\\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers","created":"2024-05-31","cited_by_count":7,"area":null},{"id":"2511.00423","title":"Bootstrap Off-policy with World Model","created":"2025-11-01","cited_by_count":7,"area":"wm"},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2110.01954","title":"Continuous-Time Fitted Value Iteration for Robust Policies","created":"2021-10-05","cited_by_count":6,"area":null},{"id":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2204.09418","title":"Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2303.03955","title":"Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2306.08888","title":"ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2309.12671","title":"How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2406.01361","title":"Learning to Play Atari in a World of Tokens","created":"2024-06-03","cited_by_count":6,"area":"wm"},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2410.11711","title":"Zero-shot Model-based Reinforcement Learning using Large Language Models","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2411.02446","title":"Learning World Models for Unconstrained Goal Navigation","created":"2024-11-03","cited_by_count":6,"area":"wm"},{"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":"2111.05819","title":"Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention","created":"2021-11-10","cited_by_count":5,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2306.14601","title":"Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception","created":"2023-06-26","cited_by_count":5,"area":null},{"id":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"id":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","cited_by_count":5,"area":null},{"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":"2101.09933","title":"A Survey on Active Deep Learning: From Model-driven to Data-driven","created":"2021-01-25","cited_by_count":4,"area":null},{"id":"2303.14265","title":"Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2305.14223","title":"Co-Learning Empirical Games and World Models","created":"2023-05-23","cited_by_count":4,"area":"wm"},{"id":"2311.18393","title":"Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2312.11348","title":"Monte Carlo Tree Search in the Presence of Transition Uncertainty","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2411.14246","title":"Simulation-Aided Policy Tuning for Black-Box Robot Learning","created":"2024-11-21","cited_by_count":4,"area":null},{"id":"2412.14312","title":"Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning","created":"2024-12-18","cited_by_count":4,"area":"deeprl"},{"id":"2105.05716","title":"Acting upon Imagination: when to trust imagined trajectories in model based reinforcement learning","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2106.12194","title":"Uncertainty-Aware Model-Based Reinforcement Learning with Application to Autonomous Driving","created":"2021-06-23","cited_by_count":3,"area":"driving"},{"id":"2110.01833","title":"Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2203.14660","title":"Revisiting Model-based Value Expansion","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2408.07644","title":"SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning","created":"2024-08-14","cited_by_count":3,"area":null},{"id":"2408.14518","title":"A Survey on Reinforcement Learning Applications in SLAM","created":"2024-08-26","cited_by_count":3,"area":"deeprl"},{"id":"2510.12312","title":"Deep SPI: Safe Policy Improvement via World Models","created":"2025-10-14","cited_by_count":3,"area":"wm"}],"next_cursor":"100"}