{"total":165,"rows":[{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2203.09168","title":"On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks","created":"2022-03-17","cited_by_count":120,"area":null},{"id":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96,"area":null},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2502.14819","title":"Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models","created":"2025-02-20","cited_by_count":89,"area":null},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2202.06985","title":"Deep Ensembles Work, But Are They Necessary?","created":"2022-02-14","cited_by_count":63,"area":null},{"id":"2109.10254","title":"Uncertainty Toolbox: an Open-Source Library for Assessing, Visualizing, and Improving Uncertainty Quantification","created":"2021-09-21","cited_by_count":57,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2310.15145","title":"Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning","created":"2023-10-23","cited_by_count":54,"area":null},{"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":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","cited_by_count":48,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2410.23208","title":"Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks","created":"2024-10-30","cited_by_count":45,"area":null},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2108.01846","title":"Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations","created":"2021-08-04","cited_by_count":39,"area":null},{"id":"2102.07970","title":"Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2212.09184","title":"Faithful Heteroscedastic Regression with Neural Networks","created":"2022-12-18","cited_by_count":37,"area":null},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35,"area":null},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2108.01832","title":"Offline Decentralized Multi-Agent Reinforcement Learning","created":"2021-08-04","cited_by_count":33,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31,"area":null},{"id":"2211.11349","title":"Data-Driven Offline Decision-Making via Invariant Representation Learning","created":"2022-11-21","cited_by_count":31,"area":null},{"id":"2104.02293","title":"On the Optimality of Batch Policy Optimization Algorithms","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2206.10524","title":"Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control","created":"2022-06-21","cited_by_count":28,"area":null},{"id":"2110.02128","title":"NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL","created":"2021-10-05","cited_by_count":27,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2304.13723","title":"A Control-Centric Benchmark for Video Prediction","created":"2023-04-26","cited_by_count":25,"area":null},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2112.10504","title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic","created":"2021-12-16","cited_by_count":23,"area":null},{"id":"2306.03346","title":"Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2207.08673","title":"Back to the Manifold: Recovering from Out-of-Distribution States","created":"2022-07-18","cited_by_count":20,"area":null},{"id":"2106.01151","title":"Towards Deeper Deep Reinforcement Learning with Spectral Normalization","created":"2021-06-02","cited_by_count":19,"area":null},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"area":null},{"id":"2305.09648","title":"Prompt-Tuning Decision Transformer with Preference Ranking","created":"2023-05-16","cited_by_count":19,"area":null},{"id":"2102.09850","title":"Model-Invariant State Abstractions for Model-Based Reinforcement Learning","created":"2021-02-19","cited_by_count":18,"area":null},{"id":"2110.04507","title":"TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations","created":"2021-10-09","cited_by_count":18,"area":null},{"id":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","cited_by_count":18,"area":null},{"id":"2306.09210","title":"Optimal Exploration for Model-Based RL in Nonlinear Systems","created":"2023-06-15","cited_by_count":18,"area":null},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","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":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2112.07701","title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning","created":"2021-12-14","cited_by_count":16,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2110.03244","title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver","created":"2021-10-07","cited_by_count":14,"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":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2502.05932","title":"Skill Expansion and Composition in Parameter Space","created":"2025-02-09","cited_by_count":14,"area":null},{"id":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2310.19308","title":"Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning","created":"2023-10-30","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":"2201.02185","title":"Admissible Policy Teaching through Reward Design","created":"2022-01-06","cited_by_count":12,"area":null},{"id":"2206.04890","title":"Adversarial Counterfactual Environment Model Learning","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2507.14057","title":"Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design","created":"2025-07-18","cited_by_count":12,"area":null},{"id":"2104.11706","title":"Safe Chance Constrained Reinforcement Learning for Batch Process Control","created":"2021-04-23","cited_by_count":11,"area":null},{"id":"2203.07413","title":"Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning","created":"2022-03-14","cited_by_count":11,"area":null},{"id":"2305.18444","title":"Continual Task Allocation in Meta-Policy Network via Sparse Prompting","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2305.12663","title":"TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching","created":"2023-05-22","cited_by_count":10,"area":null},{"id":"2306.06335","title":"How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations","created":"2023-06-10","cited_by_count":10,"area":null},{"id":"2305.16483","title":"Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"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":"2303.16189","title":"Planning with Sequence Models through Iterative Energy Minimization","created":"2023-03-28","cited_by_count":8,"area":null},{"id":"2311.01059","title":"Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2209.15205","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2301.02220","title":"Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","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":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2212.05331","title":"Effects of Spectral Normalization in Multi-agent Reinforcement Learning","created":"2022-12-10","cited_by_count":6,"area":null},{"id":"2301.12056","title":"Variational Latent Branching Model for Off-Policy Evaluation","created":"2023-01-28","cited_by_count":6,"area":null},{"id":"2410.16201","title":"Theoretical Limitations of Ensembles in the Age of Overparameterization","created":"2024-10-21","cited_by_count":6,"area":null},{"id":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2110.11073","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2204.05893","title":"Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data","created":"2022-04-12","cited_by_count":5,"area":null},{"id":"2211.07092","title":"Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2305.04832","title":"Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2402.08514","title":"Counterfactual Influence in Markov Decision Processes","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2504.01766","title":"Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error","created":"2025-04-02","cited_by_count":5,"area":null},{"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":"2102.11448","title":"MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning","created":"2021-02-23","cited_by_count":4,"area":null}],"next_cursor":"100"}