{"total":302,"rows":[{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126,"area":"offlinerl"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2210.07105","title":"CORL: Research-oriented Deep Offline Reinforcement Learning Library","created":"2022-10-13","cited_by_count":119,"area":"offlinerl"},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115,"area":"offlinerl"},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76,"area":"offlinerl"},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74,"area":"alignment"},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"area":"offlinerl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"id":"2407.20109","title":"Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":42,"area":"diffusion"},{"id":"2404.06356","title":"Policy-Guided Diffusion","created":"2024-04-09","cited_by_count":41,"area":"wm"},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37,"area":"offlinerl"},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36,"area":"offlinerl"},{"id":"2306.06569","title":"Policy Regularization with Dataset Constraint for Offline Reinforcement Learning","created":"2023-06-11","cited_by_count":34,"area":"offlinerl"},{"id":"2401.09750","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","created":"2024-01-18","cited_by_count":33,"area":"deeprl"},{"id":"2405.20555","title":"Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning","created":"2024-05-31","cited_by_count":33,"area":"diffusion"},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31,"area":"offlinerl"},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2402.04080","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning","created":"2024-02-06","cited_by_count":31,"area":"diffusion"},{"id":"2211.07357","title":"Controlling Commercial Cooling Systems Using Reinforcement Learning","created":"2022-11-11","cited_by_count":29,"area":null},{"id":"2306.12755","title":"Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning","created":"2023-06-22","cited_by_count":27,"area":"offlinerl"},{"id":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"area":"offlinerl"},{"id":"2309.05915","title":"ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning","created":"2023-09-12","cited_by_count":25,"area":"offlinerl"},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24,"area":"offlinerl"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2212.00124","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","created":"2022-11-30","cited_by_count":23,"area":"offlinerl"},{"id":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","cited_by_count":22,"area":"offlinerl"},{"id":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21,"area":"moe"},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2306.06871","title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles","created":"2023-06-12","cited_by_count":20,"area":"offlinerl"},{"id":"2310.04411","title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL","created":"2023-10-06","cited_by_count":20,"area":"offlinerl"},{"id":"2310.20025","title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","created":"2023-10-30","cited_by_count":20,"area":"offlinerl"},{"id":"2311.08935","title":"Supported Trust Region Optimization for Offline Reinforcement Learning","created":"2023-11-15","cited_by_count":20,"area":"offlinerl"},{"id":"2502.04778","title":"Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning","created":"2025-02-07","cited_by_count":20,"area":"diffusion"},{"id":"2306.04220","title":"Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL","created":"2023-06-07","cited_by_count":18,"area":"offlinerl"},{"id":"2407.00699","title":"Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning","created":"2024-06-30","cited_by_count":17,"area":"offlinerl"},{"id":"2410.19400","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","created":"2024-10-25","cited_by_count":17,"area":"offlinerl"},{"id":"2512.24138","title":"GARDO: Reinforcing Diffusion Models without Reward Hacking","created":"2025-12-30","cited_by_count":17,"area":"diffusion"},{"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":"2211.00164","title":"Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information","created":"2022-10-31","cited_by_count":16,"area":"offlinerl"},{"id":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","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":"2307.11352","title":"Model-based Offline Reinforcement Learning with Count-based Conservatism","created":"2023-07-21","cited_by_count":16,"area":"offlinerl"},{"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":"2312.07685","title":"A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning","created":"2023-12-12","cited_by_count":15,"area":"offlinerl"},{"id":"2404.02429","title":"AD4RL: Autonomous Driving Benchmarks for Offline Reinforcement Learning with Value-based Dataset","created":"2024-04-03","cited_by_count":15,"area":"driving"},{"id":"2211.01052","title":"Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints","created":"2022-11-02","cited_by_count":13,"area":"offlinerl"},{"id":"2304.04660","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","created":"2023-04-10","cited_by_count":13,"area":"offlinerl"},{"id":"2306.04875","title":"Instructed Diffuser with Temporal Condition Guidance for Offline Reinforcement Learning","created":"2023-06-08","cited_by_count":13,"area":"diffusion"},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2210.07484","title":"Mutual Information Regularized Offline Reinforcement Learning","created":"2022-10-14","cited_by_count":12,"area":"offlinerl"},{"id":"2211.00863","title":"Behavior Prior Representation learning for Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":12,"area":"offlinerl"},{"id":"2303.14716","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","created":"2023-03-26","cited_by_count":12,"area":"offlinerl"},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","cited_by_count":12,"area":"offlinerl"},{"id":"2310.05422","title":"Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning","created":"2023-10-09","cited_by_count":12,"area":"offlinerl"},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","cited_by_count":11,"area":"offlinerl"},{"id":"2410.11234","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","created":"2024-10-15","cited_by_count":11,"area":"offlinerl"},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"id":"2302.13493","title":"The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning","created":"2023-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2306.05726","title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning","created":"2023-06-09","cited_by_count":10,"area":"offlinerl"},{"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":"2402.08078","title":"Large Language Models as Agents in Two-Player Games","created":"2024-02-12","cited_by_count":10,"area":"agents"},{"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":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2110.12468","title":"False Correlation Reduction for Offline Reinforcement Learning","created":"2021-10-24","cited_by_count":9,"area":"offlinerl"},{"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":"2310.07747","title":"Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples","created":"2023-10-11","cited_by_count":9,"area":"offlinerl"},{"id":"2312.03991","title":"MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator","created":"2023-12-07","cited_by_count":9,"area":"offlinerl"},{"id":"2508.06806","title":"Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation","created":"2025-08-09","cited_by_count":9,"area":"offlinerl"},{"id":"2201.13357","title":"DNS: Determinantal Point Process Based Neural Network Sampler for Ensemble Reinforcement Learning","created":"2022-01-31","cited_by_count":8,"area":null},{"id":"2301.11734","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","created":"2023-01-27","cited_by_count":8,"area":"offlinerl"},{"id":"2306.07541","title":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","created":"2023-06-13","cited_by_count":8,"area":"offlinerl"},{"id":"2306.14479","title":"Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization","created":"2023-06-26","cited_by_count":8,"area":"offlinerl"},{"id":"2309.16397","title":"Uncertainty-Aware Decision Transformer for Stochastic Driving Environments","created":"2023-09-28","cited_by_count":8,"area":"driving"},{"id":"2401.03137","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","created":"2024-01-06","cited_by_count":8,"area":null},{"id":"2402.12527","title":"The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning","created":"2024-02-19","cited_by_count":8,"area":"offlinerl"},{"id":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"},{"id":"2406.12550","title":"Offline Imitation Learning with Model-based Reverse Augmentation","created":"2024-06-18","cited_by_count":8,"area":"offlinerl"},{"id":"2410.01954","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","created":"2024-10-02","cited_by_count":8,"area":"offlinerl"},{"id":"2411.00465","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","created":"2024-11-01","cited_by_count":8,"area":"offlinerl"},{"id":"2602.02900","title":"Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning","created":"2026-02-02","cited_by_count":8,"area":"offlinerl"}],"next_cursor":"100"}