{"total":119,"rows":[{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238,"area":"offlinerl"},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2305.09836","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","created":"2023-05-16","cited_by_count":126,"area":"offlinerl"},{"id":"2305.18459","title":"Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning","created":"2023-05-29","cited_by_count":115,"area":"diffusion"},{"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":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"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":"2406.09509","title":"CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making","created":"2024-06-13","cited_by_count":39,"area":"diffusion"},{"id":"2402.02439","title":"DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching","created":"2024-02-04","cited_by_count":36,"area":"offlinerl"},{"id":"2410.05364","title":"Diffusion Model Predictive Control","created":"2024-10-07","cited_by_count":36,"area":"diffusion"},{"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":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27,"area":null},{"id":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"area":"offlinerl"},{"id":"2311.03351","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","created":"2023-11-06","cited_by_count":26,"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":"2405.08740","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","created":"2024-05-14","cited_by_count":25,"area":"offlinerl"},{"id":"2410.20750","title":"ODRL: A Benchmark for Off-Dynamics Reinforcement Learning","created":"2024-10-28","cited_by_count":25,"area":"deeprl"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2405.16907","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":22,"area":"offlinerl"},{"id":"2402.02423","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","created":"2024-02-04","cited_by_count":21,"area":"alignment"},{"id":"2409.04180","title":"The Prevalence of Neural Collapse in Neural Multivariate Regression","created":"2024-09-06","cited_by_count":21,"area":null},{"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":"2405.18187","title":"AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization","created":"2024-05-28","cited_by_count":19,"area":"offlinerl"},{"id":"2511.13035","title":"One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow","created":"2025-11-17","cited_by_count":18,"area":"offlinerl"},{"id":"2407.12448","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","created":"2024-07-17","cited_by_count":17,"area":"diffusion"},{"id":"2306.00867","title":"IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control","created":"2023-06-01","cited_by_count":14,"area":"offlinerl"},{"id":"2311.00267","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","created":"2023-11-01","cited_by_count":14,"area":"offlinerl"},{"id":"2408.04190","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","created":"2024-08-08","cited_by_count":14,"area":"alignment"},{"id":"2506.21427","title":"Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning","created":"2025-06-26","cited_by_count":14,"area":"diffusion"},{"id":"2405.19909","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","created":"2024-05-30","cited_by_count":13,"area":"offlinerl"},{"id":"2406.11978","title":"Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner","created":"2024-06-17","cited_by_count":13,"area":"agents"},{"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":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","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":"2306.00321","title":"Improving Offline RL by Blending Heuristics","created":"2023-06-01","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":"2501.19400","title":"Vintix: Action Model via In-Context Reinforcement Learning","created":"2025-01-31","cited_by_count":10,"area":"deeprl"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2410.14069","title":"Rethinking Optimal Transport in Offline Reinforcement Learning","created":"2024-10-17","cited_by_count":9,"area":"offlinerl"},{"id":"2412.18855","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","created":"2024-12-25","cited_by_count":9,"area":"offlinerl"},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"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":"2509.23087","title":"Unleashing Flow Policies with Distributional Critics","created":"2025-09-27","cited_by_count":8,"area":"offlinerl"},{"id":"2411.01958","title":"N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs","created":"2024-11-04","cited_by_count":7,"area":"deeprl"},{"id":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2507.08761","title":"Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data","created":"2025-07-11","cited_by_count":7,"area":"deeprl"},{"id":"2305.03097","title":"Federated Ensemble-Directed Offline Reinforcement Learning","created":"2023-05-04","cited_by_count":6,"area":"offlinerl"},{"id":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"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":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"id":"2306.08772","title":"Katakomba: Tools and Benchmarks for Data-Driven NetHack","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2505.19923","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2601.10471","title":"DeFlow: Decoupling Manifold Modeling and Value Maximization for Offline Policy Extraction","created":"2026-01-15","cited_by_count":5,"area":"diffusion"},{"id":"2402.09695","title":"Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning","created":"2024-02-15","cited_by_count":4,"area":"offlinerl"},{"id":"2406.06309","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","created":"2024-06-10","cited_by_count":4,"area":"offlinerl"},{"id":"2412.20519","title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning","created":"2024-12-29","cited_by_count":4,"area":"offlinerl"},{"id":"2505.05968","title":"Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition","created":"2025-05-09","cited_by_count":4,"area":"offlinerl"},{"id":"2606.00350","title":"Drift Q-Learning","created":"2026-05-29","cited_by_count":4,"area":"offlinerl"},{"id":"2306.15503","title":"Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning","created":"2023-06-27","cited_by_count":3,"area":"offlinerl"},{"id":"2402.01812","title":"Distilling LLMs' Decomposition Abilities into Compact Language Models","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2404.16399","title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning","created":"2024-04-25","cited_by_count":3,"area":"offlinerl"},{"id":"2408.02165","title":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","created":"2024-08-04","cited_by_count":3,"area":"offlinerl"},{"id":"2512.10510","title":"Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning","created":"2025-12-11","cited_by_count":3,"area":"offlinerl"},{"id":"2602.09580","title":"SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2401.11630","title":"Solving Offline Reinforcement Learning with Decision Tree Regression","created":"2024-01-21","cited_by_count":2,"area":"offlinerl"},{"id":"2403.15502","title":"Sequential Decision-Making for Inline Text Autocomplete","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2409.07606","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","created":"2024-09-11","cited_by_count":2,"area":"offlinerl"},{"id":"2410.22728","title":"Offline Behavior Distillation","created":"2024-10-30","cited_by_count":2,"area":"deeprl"},{"id":"2411.04138","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2504.17490","title":"Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning","created":"2025-04-24","cited_by_count":2,"area":"deeprl"},{"id":"2505.09308","title":"Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model","created":"2025-05-14","cited_by_count":2,"area":null},{"id":"2506.09202","title":"Policy-Based Trajectory Clustering in Offline Reinforcement Learning","created":"2025-06-10","cited_by_count":2,"area":"offlinerl"},{"id":"2506.17155","title":"Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity","created":"2025-06-20","cited_by_count":2,"area":"offlinerl"},{"id":"2507.10174","title":"Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?","created":"2025-07-14","cited_by_count":2,"area":"offlinerl"},{"id":"2604.17919","title":"Fisher Decorator: Refining Flow Policy via a Local Transport Map","created":"2026-04-20","cited_by_count":2,"area":"diffusion"},{"id":"2605.01663","title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","created":"2026-05-03","cited_by_count":2,"area":"offlinerl"},{"id":"2306.06329","title":"HIPODE: Enhancing Offline Reinforcement Learning with High-Quality Synthetic Data from a Policy-Decoupled Approach","created":"2023-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2404.10393","title":"Offline Trajectory Optimization for Offline Reinforcement Learning","created":"2024-04-16","cited_by_count":1,"area":"offlinerl"},{"id":"2406.10445","title":"Binary Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning","created":"2024-06-14","cited_by_count":1,"area":"alignment"},{"id":"2506.00131","title":"Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization","created":"2025-05-30","cited_by_count":1,"area":"offlinerl"},{"id":"2508.19900","title":"Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning","created":"2025-08-27","cited_by_count":1,"area":"offlinerl"},{"id":"2510.12638","title":"Expert or not? assessing data quality in offline reinforcement learning","created":"2025-10-14","cited_by_count":1,"area":"offlinerl"},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2512.06692","title":"State Diversity Matters in Offline Behavior Distillation","created":"2025-12-07","cited_by_count":1,"area":"offlinerl"},{"id":"2512.07342","title":"PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning","created":"2025-12-08","cited_by_count":1,"area":"diffusion"},{"id":"2605.01968","title":"AdamO: A Collapse-Suppressed Optimizer for Offline RL","created":"2026-05-03","cited_by_count":1,"area":"offlinerl"},{"id":"2606.07592","title":"UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement Learning","created":"2026-05-28","cited_by_count":1,"area":"offlinerl"},{"id":"2405.20351","title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression","created":"2024-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2406.07117","title":"Augmenting Offline RL with Unlabeled Data","created":"2024-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2406.13376","title":"Efficient Offline Reinforcement Learning: First Imitate, then Improve","created":"2024-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2408.04198","title":"F1tenth Autonomous Racing With Offline Reinforcement Learning Methods","created":"2024-08-08","cited_by_count":0,"area":"offlinerl"},{"id":"2410.18626","title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","created":"2024-10-24","cited_by_count":0,"area":"offlinerl"},{"id":"2505.16754","title":"PyTupli: A Scalable Infrastructure for Collaborative Offline Reinforcement Learning Projects","created":"2025-05-22","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}