{"total":161,"rows":[{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2312.11456","title":"Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint","created":"2023-12-18","cited_by_count":350,"area":"alignment"},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2309.16984","title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning","created":"2023-09-29","cited_by_count":100,"area":"diffusion"},{"id":"2412.06685","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","created":"2024-12-09","cited_by_count":79,"area":"offlinerl"},{"id":"2407.13399","title":"Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization","created":"2024-07-18","cited_by_count":78,"area":"alignment"},{"id":"2511.00091","title":"Self-Improving Vision-Language-Action Models with Data Generation via Residual RL","created":"2025-10-30","cited_by_count":78,"area":"vla"},{"id":"2404.16767","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","created":"2024-04-25","cited_by_count":69,"area":"alignment"},{"id":"2311.02198","title":"Imitation Bootstrapped Reinforcement Learning","created":"2023-11-03","cited_by_count":64,"area":"offlinerl"},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63,"area":"offlinerl"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2406.01462","title":"The Importance of Online Data: Understanding Preference Fine-tuning via Coverage","created":"2024-06-03","cited_by_count":55,"area":"alignment"},{"id":"2502.01828","title":"From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment","created":"2025-02-03","cited_by_count":52,"area":"lr"},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41,"area":"alignment"},{"id":"2601.14234","title":"Q-learning with Adjoint Matching","created":"2026-01-20","cited_by_count":37,"area":"diffusion"},{"id":"2402.08848","title":"Hybrid Inverse Reinforcement Learning","created":"2024-02-13","cited_by_count":32,"area":"offlinerl"},{"id":"2403.12203","title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","created":"2024-03-18","cited_by_count":31,"area":"deeprl"},{"id":"2311.12996","title":"RLIF: Interactive Imitation Learning as Reinforcement Learning","created":"2023-11-21","cited_by_count":30,"area":"offlinerl"},{"id":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"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":"2211.12612","title":"Transfer Learning for Contextual Multi-armed Bandits","created":"2022-11-22","cited_by_count":24,"area":null},{"id":"2505.20686","title":"Accelerating RL for LLM Reasoning with Optimal Advantage Regression","created":"2025-05-27","cited_by_count":24,"area":"lr"},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2410.20254","title":"Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL","created":"2024-10-26","cited_by_count":21,"area":"deeprl"},{"id":"2505.17826","title":"Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models","created":"2025-05-23","cited_by_count":19,"area":null},{"id":"2309.12716","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","created":"2023-09-22","cited_by_count":17,"area":"offlinerl"},{"id":"2310.01737","title":"Blending Imitation and Reinforcement Learning for Robust Policy Improvement","created":"2023-10-03","cited_by_count":17,"area":null},{"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":"2305.10282","title":"Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning","created":"2023-05-17","cited_by_count":16,"area":"offlinerl"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2309.03322","title":"REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation","created":"2023-09-06","cited_by_count":15,"area":"offlinerl"},{"id":"2505.08078","title":"What Matters for Batch Online Reinforcement Learning in Robotics?","created":"2025-05-12","cited_by_count":15,"area":"offlinerl"},{"id":"2605.00416","title":"Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies","created":"2026-05-01","cited_by_count":15,"area":"vla"},{"id":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14,"area":"offlinerl"},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"area":"offlinerl"},{"id":"2302.00662","title":"Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders","created":"2023-02-01","cited_by_count":13,"area":"offlinerl"},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2410.18076","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"area":null},{"id":"2408.08441","title":"D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning","created":"2024-08-15","cited_by_count":12,"area":"offlinerl"},{"id":"2506.07505","title":"Reinforcement Learning via Implicit Imitation Guidance","created":"2025-06-09","cited_by_count":12,"area":"offlinerl"},{"id":"2507.14057","title":"Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design","created":"2025-07-18","cited_by_count":12,"area":null},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"area":"offlinerl"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2311.15951","title":"Replay across Experiments: A Natural Extension of Off-Policy RL","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"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":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"id":"2505.23062","title":"Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data","created":"2025-05-29","cited_by_count":9,"area":"diffusion"},{"id":"2511.18606","title":"How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints","created":"2025-11-23","cited_by_count":9,"area":null},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8,"area":"deeprl"},{"id":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","cited_by_count":8,"area":"offlinerl"},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2310.08558","title":"Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias","created":"2023-10-12","cited_by_count":7,"area":"offlinerl"},{"id":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2604.04142","title":"OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models","created":"2026-04-05","cited_by_count":7,"area":"diffusion"},{"id":"2302.13726","title":"(Re)$^2$H2O: Autonomous Driving Scenario Generation via Reversely Regularized Hybrid Offline-and-Online Reinforcement Learning","created":"2023-02-27","cited_by_count":6,"area":"driving"},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","created":"2024-08-08","cited_by_count":6,"area":"offlinerl"},{"id":"2410.01101","title":"Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank","created":"2024-10-01","cited_by_count":6,"area":"offlinerl"},{"id":"2412.10616","title":"Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration","created":"2024-12-13","cited_by_count":6,"area":"alignment"},{"id":"2502.08259","title":"Balancing optimism and pessimism in offline-to-online learning","created":"2025-02-12","cited_by_count":6,"area":"offlinerl"},{"id":"2505.02363","title":"SIMPLEMIX: Frustratingly Simple Mixing of Off- and On-policy Data in Language Model Preference Learning","created":"2025-05-05","cited_by_count":6,"area":"alignment"},{"id":"2505.11478","title":"Automatic Reward Shaping from Confounded Offline Data","created":"2025-05-16","cited_by_count":6,"area":"deeprl"},{"id":"2510.08218","title":"Expressive Value Learning for Scalable Offline Reinforcement Learning","created":"2025-10-09","cited_by_count":6,"area":"diffusion"},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","cited_by_count":5,"area":"offlinerl"},{"id":"2402.05476","title":"Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization","created":"2024-02-08","cited_by_count":5,"area":"deeprl"},{"id":"2403.09701","title":"A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2406.07253","title":"Hybrid Reinforcement Learning from Offline Observation Alone","created":"2024-06-11","cited_by_count":5,"area":"deeprl"},{"id":"2406.11810","title":"Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics","created":"2024-06-17","cited_by_count":5,"area":"deeprl"},{"id":"2501.18873","title":"Best Policy Learning from Trajectory Preference Feedback","created":"2025-01-31","cited_by_count":5,"area":"alignment"},{"id":"2502.07937","title":"Active Advantage-Aligned Online Reinforcement Learning with Offline Data","created":"2025-02-11","cited_by_count":5,"area":"offlinerl"},{"id":"2503.13162","title":"Efficient Imitation under Misspecification","created":"2025-03-17","cited_by_count":5,"area":"offlinerl"},{"id":"2505.10442","title":"IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning","created":"2025-05-15","cited_by_count":5,"area":"offlinerl"},{"id":"2304.12886","title":"What can online reinforcement learning with function approximation benefit from general coverage conditions?","created":"2023-04-25","cited_by_count":4,"area":"offlinerl"},{"id":"2310.05723","title":"Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":"offlinerl"},{"id":"2402.08022","title":"Leveraging Digital Cousins for Ensemble Q-Learning in Large-Scale Wireless Networks","created":"2024-02-12","cited_by_count":4,"area":"deeprl"},{"id":"2405.05468","title":"Model-Free Robust $\\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data","created":"2024-05-08","cited_by_count":4,"area":"deeprl"},{"id":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2510.01460","title":"The Three Regimes of Offline-to-Online Reinforcement Learning","created":"2025-10-01","cited_by_count":4,"area":"offlinerl"},{"id":"2602.09456","title":"Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2403.19462","title":"Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization","created":"2024-03-28","cited_by_count":3,"area":"offlinerl"},{"id":"2408.13567","title":"Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning","created":"2024-08-24","cited_by_count":3,"area":null},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","cited_by_count":3,"area":"alignment"},{"id":"2510.21060","title":"On the Sample Complexity of Differentially Private Policy Optimization","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2602.20220","title":"What Matters for Simulation to Online Reinforcement Learning on Real Robots","created":"2026-02-23","cited_by_count":3,"area":"deeprl"},{"id":"2605.07727","title":"Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2606.14801","title":"QPILOTS: Efficient Test-Time Q-Steering for Flow Policies","created":"2026-06-11","cited_by_count":3,"area":"diffusion"},{"id":"2306.11271","title":"Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2404.07266","title":"Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2408.16882","title":"Coverage Analysis of Multi-Environment Q-Learning Algorithms for Wireless Network Optimization","created":"2024-08-29","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}