{"total":101,"rows":[{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300,"area":"wm"},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"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":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2305.17330","title":"MADiff: Offline Multi-agent Learning with Diffusion Models","created":"2023-05-27","cited_by_count":75,"area":"diffusion"},{"id":"2503.04975","title":"Energy-Weighted Flow Matching for Offline Reinforcement Learning","created":"2025-03-06","cited_by_count":73,"area":"diffusion"},{"id":"2406.01586","title":"ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation","created":"2024-06-03","cited_by_count":57,"area":"diffusion"},{"id":"2401.15443","title":"DiffuserLite: Towards Real-time Diffusion Planning","created":"2024-01-27","cited_by_count":42,"area":null},{"id":"2404.06356","title":"Policy-Guided Diffusion","created":"2024-04-09","cited_by_count":41,"area":"wm"},{"id":"2503.05153","title":"Generative Trajectory Stitching through Diffusion Composition","created":"2025-03-07","cited_by_count":41,"area":"diffusion"},{"id":"2307.01849","title":"Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning","created":"2023-07-04","cited_by_count":40,"area":"diffusion"},{"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":"2310.06343","title":"Boosting Continuous Control with Consistency Policy","created":"2023-10-10","cited_by_count":38,"area":"diffusion"},{"id":"2410.12822","title":"AVID: Adapting Video Diffusion Models to World Models","created":"2024-10-01","cited_by_count":37,"area":"wm"},{"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":"2402.17768","title":"Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning","created":"2024-02-27","cited_by_count":35,"area":"offlinerl"},{"id":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2312.08533","title":"World Models via Policy-Guided Trajectory Diffusion","created":"2023-12-13","cited_by_count":34,"area":"wm"},{"id":"2402.03570","title":"Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning","created":"2024-02-05","cited_by_count":31,"area":"wm"},{"id":"2405.03150","title":"Video Diffusion Models: A Survey","created":"2024-05-06","cited_by_count":30,"area":"diffusion"},{"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":"2407.12448","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","created":"2024-07-17","cited_by_count":17,"area":"diffusion"},{"id":"2501.17827","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","created":"2025-01-29","cited_by_count":17,"area":"deeprl"},{"id":"2410.08896","title":"MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2307.01472","title":"Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL","created":"2023-07-04","cited_by_count":15,"area":"diffusion"},{"id":"2406.16121","title":"Diffusion Spectral Representation for Reinforcement Learning","created":"2024-06-23","cited_by_count":15,"area":"diffusion"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2505.23527","title":"Normalizing Flows are Capable Models for Continuous Control","created":"2025-05-29","cited_by_count":14,"area":"deeprl"},{"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":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2411.16959","title":"RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations","created":"2024-11-25","cited_by_count":13,"area":"offlinerl"},{"id":"2506.00895","title":"State-Covering Trajectory Stitching for Diffusion Planners","created":"2025-06-01","cited_by_count":13,"area":"diffusion"},{"id":"2510.10304","title":"Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting","created":"2025-10-11","cited_by_count":13,"area":"agents"},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2401.03629","title":"DDM-Lag : A Diffusion-based Decision-making Model for Autonomous Vehicles with Lagrangian Safety Enhancement","created":"2024-01-08","cited_by_count":11,"area":"diffusion"},{"id":"2405.05852","title":"Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control","created":"2024-05-09","cited_by_count":11,"area":"diffusion"},{"id":"2410.00051","title":"Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization","created":"2024-09-28","cited_by_count":11,"area":"diffusion"},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","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":"2409.08687","title":"xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing","created":"2024-09-13","cited_by_count":9,"area":"diffusion"},{"id":"2506.00867","title":"Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning","created":"2025-06-01","cited_by_count":9,"area":"diffusion"},{"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":"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":"2508.06269","title":"OM2P: Offline Multi-Agent Mean-Flow Policy","created":"2025-08-08","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":"2411.10809","title":"Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay","created":"2024-11-16","cited_by_count":7,"area":"diffusion"},{"id":"2507.20499","title":"DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning","created":"2025-07-28","cited_by_count":7,"area":"diffusion"},{"id":"2410.15698","title":"Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces","created":"2024-10-21","cited_by_count":6,"area":"offlinerl"},{"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":"2506.13672","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","created":"2025-06-16","cited_by_count":6,"area":"deeprl"},{"id":"2407.09702","title":"Investigating the Interplay of Prioritized Replay and Generalization","created":"2024-07-12","cited_by_count":5,"area":"deeprl"},{"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":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2408.15501","title":"MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning","created":"2024-08-28","cited_by_count":4,"area":"diffusion"},{"id":"2412.20519","title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning","created":"2024-12-29","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":"2603.05117","title":"SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation","created":"2026-03-05","cited_by_count":4,"area":"diffusion"},{"id":"2406.12589","title":"Discovering Minimal Reinforcement Learning Environments","created":"2024-06-18","cited_by_count":3,"area":"deeprl"},{"id":"2502.00466","title":"EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling","created":"2025-02-01","cited_by_count":3,"area":"wm"},{"id":"2510.01456","title":"SCOPED: Score-Curvature Out-of-distribution Proximity Evaluator for Diffusion","created":"2025-10-01","cited_by_count":3,"area":"diffusion"},{"id":"2510.25529","title":"Off-policy Reinforcement Learning with Model-based Exploration Augmentation","created":"2025-10-29","cited_by_count":3,"area":"deeprl"},{"id":"2602.18291","title":"Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies","created":"2026-02-20","cited_by_count":3,"area":"diffusion"},{"id":"2402.00807","title":"Augmenting Offline Reinforcement Learning with State-only Interactions","created":"2024-02-01","cited_by_count":2,"area":"offlinerl"},{"id":"2405.19189","title":"DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning","created":"2024-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2502.12198","title":"Maximize Your Diffusion: A Study into Reward Maximization and Alignment for Diffusion-based Control","created":"2025-02-16","cited_by_count":2,"area":"alignment"},{"id":"2505.20781","title":"STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation","created":"2025-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2507.09534","title":"Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement Learning","created":"2025-07-13","cited_by_count":2,"area":"offlinerl"},{"id":"2510.12253","title":"Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development","created":"2025-10-14","cited_by_count":2,"area":"diffusion"},{"id":"2602.00737","title":"Pareto-Conditioned Diffusion Models for Offline Multi-Objective Optimization","created":"2026-01-31","cited_by_count":2,"area":"diffusion"},{"id":"2606.17551","title":"Reversal Q-Learning","created":"2026-06-16","cited_by_count":2,"area":"diffusion"},{"id":"2408.13092","title":"Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning","created":"2024-08-23","cited_by_count":1,"area":"diffusion"},{"id":"2410.10160","title":"Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?","created":"2024-10-14","cited_by_count":1,"area":null},{"id":"2411.18230","title":"Dependency-Aware CAV Task Scheduling via Diffusion-Based Reinforcement Learning","created":"2024-11-27","cited_by_count":1,"area":"deeprl"},{"id":"2501.06718","title":"DRDT3: Diffusion-Refined Decision Test-Time Training Model","created":"2025-01-12","cited_by_count":1,"area":"diffusion"},{"id":"2506.03522","title":"Path Generation and Evaluation in Video Games: A Nonparametric Statistical Approach","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2512.07342","title":"PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning","created":"2025-12-08","cited_by_count":1,"area":"diffusion"},{"id":"2606.05558","title":"Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents","created":"2026-06-04","cited_by_count":1,"area":"wm"},{"id":"2606.22314","title":"Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution","created":"2026-06-21","cited_by_count":1,"area":null},{"id":"2403.07136","title":"On the Limited Representational Power of Value Functions and its Links to Statistical (In)Efficiency","created":"2024-03-11","cited_by_count":0,"area":"deeprl"},{"id":"2406.00761","title":"Shared-unique Features and Task-aware Prioritized Sampling on Multi-task Reinforcement Learning","created":"2024-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2406.04323","title":"ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories","created":"2024-06-06","cited_by_count":0,"area":"deeprl"},{"id":"2406.09089","title":"DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning","created":"2024-06-13","cited_by_count":0,"area":"diffusion"},{"id":"2502.06491","title":"Model-Based Offline Reinforcement Learning with Reliability-Guaranteed Sequence Modeling","created":"2025-02-10","cited_by_count":0,"area":"offlinerl"},{"id":"2503.14833","title":"Curiosity-Diffuser: Curiosity Guide Diffusion Models for Reliability","created":"2025-03-19","cited_by_count":0,"area":"diffusion"},{"id":"2507.15356","title":"RAD: Retrieval High-quality Demonstrations to Enhance Decision-making","created":"2025-07-21","cited_by_count":0,"area":"offlinerl"},{"id":"2509.14832","title":"Diffusion-Based Scenario Tree Generation for Multivariate Time Series Prediction and Multistage Stochastic Optimization","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.03828","title":"From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning","created":"2025-11-05","cited_by_count":0,"area":"offlinerl"},{"id":"2512.10891","title":"Iterative Compositional Data Generation for Robot Control","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.13609","title":"Do-Undo Bench: Reversibility for Action Understanding in Image Generation","created":"2025-12-15","cited_by_count":0,"area":"mllm"},{"id":"2604.23308","title":"CODA: Coordination via On-Policy Diffusion for Multi-Agent Offline Reinforcement Learning","created":"2026-04-25","cited_by_count":0,"area":"offlinerl"},{"id":"2605.00159","title":"E$^2$DT: Efficient and Effective Decision Transformer with Experience-Aware Sampling for Robotic Manipulation","created":"2026-04-30","cited_by_count":0,"area":"offlinerl"},{"id":"2605.13401","title":"Trajectory-Level Data Augmentation for Offline Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2607.16090","title":"DADiff: Diffusion-Driven Cross-Domain Policy Adaptation for Reinforcement Learning","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2607.17560","title":"Reinforcement Learning: From Algorithms To Foundation Models","created":"2026-07-20","cited_by_count":0,"area":"wm"},{"id":"2607.25123","title":"Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2608.03069","title":"Revisiting TD Target Aggregation under Uncertainty in Q-Learning","created":"2026-08-04","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}