{"total":231,"rows":[{"id":"2211.04486","title":"Active Example Selection for In-Context Learning","created":"2022-11-08","cited_by_count":196,"area":null},{"id":"2302.01877","title":"AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners","created":"2023-02-03","cited_by_count":149,"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":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114,"area":null},{"id":"2505.19789","title":"What Can RL Bring to VLA Generalization? An Empirical Study","created":"2025-05-26","cited_by_count":108,"area":"vla"},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"2309.12659","title":"OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling","created":"2023-09-22","cited_by_count":74,"area":null},{"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":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2410.04350","title":"TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights","created":"2024-10-06","cited_by_count":42,"area":"alignment"},{"id":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39,"area":"alignment"},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"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":"2306.06569","title":"Policy Regularization with Dataset Constraint for Offline Reinforcement Learning","created":"2023-06-11","cited_by_count":34,"area":"offlinerl"},{"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":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"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":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"area":"offlinerl"},{"id":"2502.18906","title":"VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model","created":"2025-02-26","cited_by_count":19,"area":"lr"},{"id":"2210.06479","title":"Real World Offline Reinforcement Learning with Realistic Data Source","created":"2022-10-12","cited_by_count":17,"area":"offlinerl"},{"id":"2504.16680","title":"Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots","created":"2025-04-23","cited_by_count":17,"area":"wm"},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2503.17286","title":"Offline Model-Based Optimization: Comprehensive Review","created":"2025-03-21","cited_by_count":15,"area":null},{"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":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"area":null},{"id":"2411.16313","title":"CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning","created":"2024-11-25","cited_by_count":14,"area":null},{"id":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","cited_by_count":13,"area":"offlinerl"},{"id":"2210.13111","title":"Federated Learning and Meta Learning: Approaches, Applications, and Directions","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2306.03362","title":"Boosting Offline Reinforcement Learning with Action Preference Query","created":"2023-06-06","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":"2301.09544","title":"Learning to View: Decision Transformers for Active Object Detection","created":"2023-01-23","cited_by_count":11,"area":"offlinerl"},{"id":"2309.03081","title":"ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":11,"area":"offlinerl"},{"id":"2312.02682","title":"H-GAP: Humanoid Control with a Generalist Planner","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2403.07262","title":"A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective","created":"2024-03-12","cited_by_count":11,"area":"offlinerl"},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"id":"2310.02505","title":"Learning to Reach Goals via Diffusion","created":"2023-10-04","cited_by_count":10,"area":"diffusion"},{"id":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","cited_by_count":10,"area":"deeprl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","cited_by_count":9,"area":"offlinerl"},{"id":"2406.09068","title":"Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation","created":"2024-06-13","cited_by_count":9,"area":"offlinerl"},{"id":"2507.02712","title":"A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control","created":"2025-07-03","cited_by_count":9,"area":"deeprl"},{"id":"2302.00521","title":"Off-the-Grid MARL: Datasets with Baselines for Offline Multi-Agent Reinforcement Learning","created":"2023-02-01","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":"2308.01490","title":"Minimax Optimal Q Learning with Nearest Neighbors","created":"2023-08-03","cited_by_count":8,"area":null},{"id":"2405.19878","title":"Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Models","created":"2024-05-30","cited_by_count":8,"area":"wm"},{"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"},{"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":"2305.03360","title":"A Survey on Offline Model-Based Reinforcement Learning","created":"2023-05-05","cited_by_count":7,"area":"offlinerl"},{"id":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2404.12530","title":"TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents","created":"2024-04-18","cited_by_count":7,"area":"offlinerl"},{"id":"2405.12094","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","created":"2024-05-20","cited_by_count":7,"area":"ssm"},{"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":"2505.19053","title":"Structured Reinforcement Learning for Combinatorial Decision-Making","created":"2025-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2511.00423","title":"Bootstrap Off-policy with World Model","created":"2025-11-01","cited_by_count":7,"area":"wm"},{"id":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6,"area":"offlinerl"},{"id":"2403.07309","title":"Reinforced Sequential Decision-Making for Sepsis Treatment: The POSNEGDM Framework with Mortality Classifier and Transformer","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2409.10589","title":"Offline Reinforcement Learning for Learning to Dispatch for Job Shop Scheduling","created":"2024-09-16","cited_by_count":6,"area":"offlinerl"},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"id":"2303.09209","title":"Learning optimal policies from event logs through reinforcement learning: a comparison of deep and MDP-based approaches","created":"2023-03-16","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2403.01734","title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","created":"2024-03-04","cited_by_count":5,"area":"offlinerl"},{"id":"2407.01343","title":"Coordination Failure in Cooperative Offline MARL","created":"2024-07-01","cited_by_count":5,"area":"offlinerl"},{"id":"2407.20299","title":"Dataset Distillation for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":5,"area":"offlinerl"},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2502.07937","title":"Active Advantage-Aligned Online Reinforcement Learning with Offline Data","created":"2025-02-11","cited_by_count":5,"area":"offlinerl"},{"id":"2510.22686","title":"FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement Learning","created":"2025-10-26","cited_by_count":5,"area":"diffusion"},{"id":"2512.02350","title":"FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Data","created":"2025-12-02","cited_by_count":5,"area":"offlinerl"},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2304.00354","title":"On Context Distribution Shift in Task Representation Learning for Offline Meta RL","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2309.08925","title":"DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning","created":"2023-09-16","cited_by_count":4,"area":"offlinerl"},{"id":"2409.12001","title":"Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning","created":"2024-09-18","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":"2502.15968","title":"Enhancing PPO with Trajectory-Aware Hybrid Policies","created":"2025-02-21","cited_by_count":4,"area":"deeprl"},{"id":"2504.04395","title":"Human-Level Competitive Pok\\'emon via Scalable Offline Reinforcement Learning with Transformers","created":"2025-04-06","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":"2506.05762","title":"BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning","created":"2025-06-06","cited_by_count":4,"area":"diffusion"},{"id":"2509.13341","title":"Imagined Autocurricula","created":"2025-09-11","cited_by_count":4,"area":"wm"},{"id":"2203.03003","title":"Offline Deep Reinforcement Learning for Dynamic Pricing of Consumer Credit","created":"2022-03-06","cited_by_count":3,"area":"offlinerl"},{"id":"2302.08865","title":"Swapped goal-conditioned offline reinforcement learning","created":"2023-02-17","cited_by_count":3,"area":"offlinerl"},{"id":"2308.06935","title":"Insurance pricing on price comparison websites via reinforcement learning","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2308.07741","title":"Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World","created":"2023-08-15","cited_by_count":3,"area":"offlinerl"},{"id":"2309.07578","title":"Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning","created":"2023-09-14","cited_by_count":3,"area":"offlinerl"},{"id":"2407.00681","title":"Safe Reinforcement Learning for Power System Control: A Review","created":"2024-06-30","cited_by_count":3,"area":"deeprl"},{"id":"2409.09653","title":"KAN v.s. MLP for Offline Reinforcement Learning","created":"2024-09-15","cited_by_count":3,"area":"offlinerl"},{"id":"2503.06302","title":"Synergizing AI and Digital Twins for Next-Generation Network Optimization, Forecasting, and Security","created":"2025-03-08","cited_by_count":3,"area":null},{"id":"2505.20621","title":"Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning","created":"2025-05-27","cited_by_count":3,"area":"offlinerl"},{"id":"2509.19305","title":"Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning","created":"2025-09-04","cited_by_count":3,"area":"diffusion"},{"id":"2512.08280","title":"Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making","created":"2025-12-09","cited_by_count":3,"area":"diffusion"},{"id":"2512.10510","title":"Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning","created":"2025-12-11","cited_by_count":3,"area":"offlinerl"},{"id":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2603.08118","title":"Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting","created":"2026-03-09","cited_by_count":3,"area":"offlinerl"}],"next_cursor":"100"}