{"total":89,"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":"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":"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":"2506.12811","title":"Flow-Based Policy for Online Reinforcement Learning","created":"2025-06-15","cited_by_count":37,"area":"deeprl"},{"id":"2601.14234","title":"Q-learning with Adjoint Matching","created":"2026-01-20","cited_by_count":37,"area":"diffusion"},{"id":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"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":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2507.23675","title":"One-Step Flow Policy Mirror Descent","created":"2025-07-31","cited_by_count":21,"area":"diffusion"},{"id":"2502.15760","title":"Digi-Q: Learning Q-Value Functions for Training Device-Control Agents","created":"2025-02-13","cited_by_count":20,"area":"agents"},{"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":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"area":"deeprl"},{"id":"2509.06782","title":"Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning","created":"2025-09-08","cited_by_count":15,"area":"offlinerl"},{"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":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2506.07744","title":"Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning","created":"2025-06-09","cited_by_count":12,"area":"offlinerl"},{"id":"2510.22512","title":"Transitive RL: Value Learning via Divide and Conquer","created":"2025-10-26","cited_by_count":12,"area":"deeprl"},{"id":"2505.14975","title":"Flattening Hierarchies with Policy Bootstrapping","created":"2025-05-20","cited_by_count":11,"area":"synth"},{"id":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10,"area":"offlinerl"},{"id":"2511.05005","title":"Multi-agent Coordination via Flow Matching","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2512.03973","title":"Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning","created":"2025-12-03","cited_by_count":9,"area":"offlinerl"},{"id":"2511.07730","title":"Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning","created":"2025-11-11","cited_by_count":8,"area":"deeprl"},{"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":"2510.15382","title":"Towards Robust Zero-Shot Reinforcement Learning","created":"2025-10-17","cited_by_count":7,"area":"deeprl"},{"id":"2505.14403","title":"Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning","created":"2025-05-20","cited_by_count":6,"area":"lr"},{"id":"2510.08218","title":"Expressive Value Learning for Scalable Offline Reinforcement Learning","created":"2025-10-09","cited_by_count":6,"area":"diffusion"},{"id":"2601.00898","title":"Dichotomous Diffusion Policy Optimization","created":"2025-12-31","cited_by_count":6,"area":"diffusion"},{"id":"2605.13435","title":"Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy","created":"2026-05-13","cited_by_count":6,"area":"deeprl"},{"id":"2606.11087","title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","created":"2026-06-09","cited_by_count":6,"area":"offlinerl"},{"id":"2407.12163","title":"Bellman Diffusion Models","created":"2024-07-16","cited_by_count":5,"area":"diffusion"},{"id":"2510.19495","title":"Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning","created":"2025-10-22","cited_by_count":5,"area":"offlinerl"},{"id":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"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":"2603.15136","title":"Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies","created":"2026-03-16","cited_by_count":4,"area":"offlinerl"},{"id":"2605.26552","title":"Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference","created":"2026-05-26","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":"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":"2603.04333","title":"What Does Flow Matching Bring To TD Learning?","created":"2026-03-04","cited_by_count":2,"area":"diffusion"},{"id":"2603.08399","title":"A Recipe for Stable Offline Multi-agent Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"offlinerl"},{"id":"2603.09344","title":"Robust Regularized Policy Iteration under Transition Uncertainty","created":"2026-03-10","cited_by_count":2,"area":"offlinerl"},{"id":"2603.27400","title":"Rainbow-DemoRL: Combining Improvements in Demonstration-Augmented Reinforcement Learning","created":"2026-03-28","cited_by_count":2,"area":"deeprl"},{"id":"2604.08958","title":"WOMBET: World Model-Based Experience Transfer for Robust and Sample-efficient Reinforcement Learning","created":"2026-04-10","cited_by_count":2,"area":"wm"},{"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":"2605.22711","title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-21","cited_by_count":2,"area":"offlinerl"},{"id":"2606.03698","title":"Multi$^2$: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.10613","title":"Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning","created":"2026-06-09","cited_by_count":2,"area":"offlinerl"},{"id":"2606.17551","title":"Reversal Q-Learning","created":"2026-06-16","cited_by_count":2,"area":"diffusion"},{"id":"2608.20909","title":"Decoupling Policy Extraction for Offline Reinforcement Learning","created":"2026-08-21","cited_by_count":2,"area":"offlinerl"},{"id":"2412.18781","title":"Robustness Evaluation of Offline Reinforcement Learning for Robot Control Against Action Perturbations","created":"2024-12-25","cited_by_count":1,"area":"offlinerl"},{"id":"2506.08681","title":"Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling","created":"2025-06-10","cited_by_count":1,"area":"alignment"},{"id":"2509.06201","title":"Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control","created":"2025-09-07","cited_by_count":1,"area":null},{"id":"2510.14000","title":"A Diffusion-Refined Planner with Reinforcement Learning Priors for Confined-Space Parking","created":"2025-10-15","cited_by_count":1,"area":"deeprl"},{"id":"2604.20627","title":"Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning","created":"2026-04-22","cited_by_count":1,"area":"wm"},{"id":"2605.07393","title":"Offline Policy Optimization with Posterior Sampling","created":"2026-05-08","cited_by_count":1,"area":"offlinerl"},{"id":"2605.09364","title":"MSPR: Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","created":"2026-05-10","cited_by_count":1,"area":"deeprl"},{"id":"2411.06815","title":"Streetwise Agents: Empowering Offline RL Policies to Outsmart Exogenous Stochastic Disturbances in RTC","created":"2024-11-11","cited_by_count":0,"area":"offlinerl"},{"id":"2507.13491","title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","created":"2025-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2507.15356","title":"RAD: Retrieval High-quality Demonstrations to Enhance Decision-making","created":"2025-07-21","cited_by_count":0,"area":"offlinerl"},{"id":"2511.11973","title":"Quantile Q-Learning: Revisiting Offline Extreme Q-Learning with Quantile Regression","created":"2025-11-15","cited_by_count":0,"area":"offlinerl"},{"id":"2512.01987","title":"Forecasting in Offline Reinforcement Learning for Non-stationary Environments","created":"2025-12-01","cited_by_count":0,"area":"offlinerl"},{"id":"2602.05459","title":"Beyond Success Rates: Trainability and Extractability for Offline GCRL","created":"2026-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2604.12509","title":"Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2606.00680","title":"Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief","created":"2026-05-30","cited_by_count":0,"area":"offlinerl"},{"id":"2606.21136","title":"Horizon Adaptive Offline Policy Learning via Value Stitching","created":"2026-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2607.02288","title":"Generalization in offline RL: The structure is more important than the amount of pessimism","created":"2026-07-02","cited_by_count":0,"area":"offlinerl"},{"id":"2608.01205","title":"ReBRAC-v2: The Return of the King","created":"2026-08-02","cited_by_count":0,"area":"offlinerl"},{"id":"2608.02034","title":"Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement Learning","created":"2026-08-03","cited_by_count":0,"area":"deeprl"},{"id":"2608.28065","title":"Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning","created":"2026-08-28","cited_by_count":0,"area":"offlinerl"},{"id":"2609.03842","title":"Multi-step Proximal Policy Improvement in Offline Reinforcement Learning","created":"2026-09-03","cited_by_count":0,"area":"offlinerl"},{"id":"2609.15883","title":"Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport","created":"2026-09-14","cited_by_count":0,"area":"offlinerl"},{"id":"2609.24489","title":"Lifted Bellman Linear Programming for Offline Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"offlinerl"},{"id":"2609.24750","title":"Reinforcement Learning in Operational Research: A Technical Review and Practical Roadmap","created":"2026-09-21","cited_by_count":0,"area":"deeprl"},{"id":"2609.30391","title":"From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning","created":"2026-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2609.33259","title":"GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences","created":"2026-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35880","title":"From Static Policies to Adaptive Priors in Offline Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2609.37432","title":"Looped Actor: Depth-Recurrent Reasoning Models for Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.40149","title":"Role-Adaptive Policy Optimization for Offline Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2610.02554","title":"Test-time Multi-agent Coordination by Decomposed Value Gradient Flow","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.12135","title":"Q-Shaped Options for Hierarchical Reinforcement Learning","created":"2026-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2610.14941","title":"Compositional Average Velocity Modeling for Efficient Diffusion Offline Reinforcement Learning","created":"2026-10-10","cited_by_count":0,"area":"diffusion"},{"id":"2610.19883","title":"Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction","created":"2026-10-14","cited_by_count":0,"area":"deeprl"},{"id":"2610.20190","title":"Value-Guided Repulsion for Offline Reinforcement Learning","created":"2026-10-14","cited_by_count":0,"area":"offlinerl"},{"id":"2610.20318","title":"Efficient Test-Time Adaptation For Robot Policies","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}