{"list":"other","total":67,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2407.15595","title":"Discrete Flow Matching","created":"2024-07-22","cited_by_count":317},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302},{"id":"2412.06264","title":"Flow Matching Guide and Code","created":"2024-12-09","cited_by_count":301},{"id":"1902.00275","title":"Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design","created":"2019-02-01","cited_by_count":262},{"id":"2307.08698","title":"Flow Matching in Latent Space","created":"2023-07-17","cited_by_count":160},{"id":"2008.05556","title":"Model-Based Offline Planning","created":"2020-08-12","cited_by_count":129},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125},{"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},{"id":"2405.16173","title":"Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization","created":"2024-05-25","cited_by_count":110},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106},{"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},{"id":"2311.13443","title":"Guided Flows for Generative Modeling and Decision Making","created":"2023-11-22","cited_by_count":101},{"id":"2412.15205","title":"FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching","created":"2024-12-19","cited_by_count":80},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74},{"id":"2401.02644","title":"Simple Hierarchical Planning with Diffusion","created":"2024-01-05","cited_by_count":73},{"id":"2405.14664","title":"Fisher Flow Matching for Generative Modeling over Discrete Data","created":"2024-05-23","cited_by_count":72},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57},{"id":"2310.16338","title":"Generative Pre-training for Speech with Flow Matching","created":"2023-10-25","cited_by_count":55},{"id":"2409.01083","title":"Affordance-based Robot Manipulation with Flow Matching","created":"2024-09-02","cited_by_count":54},{"id":"2410.23405","title":"FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions","created":"2024-10-30","cited_by_count":53},{"id":"2207.02200","title":"Offline RL Policies Should be Trained to be Adaptive","created":"2022-07-05","cited_by_count":52},{"id":"2406.00681","title":"Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient","created":"2024-06-02","cited_by_count":51},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44},{"id":"2401.15443","title":"DiffuserLite: Towards Real-time Diffusion Planning","created":"2024-01-27","cited_by_count":42},{"id":"2402.02439","title":"DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching","created":"2024-02-04","cited_by_count":36},{"id":"2010.13129","title":"ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows","created":"2020-10-25","cited_by_count":33},{"id":"2407.12381","title":"Flow Matching Imitation Learning for Multi-Support Manipulation","created":"2024-07-17","cited_by_count":29},{"id":"2303.03747","title":"Graph Decision Transformer","created":"2023-03-07","cited_by_count":20},{"id":"2301.12203","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","created":"2023-01-28","cited_by_count":16},{"id":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13},{"id":"2002.06473","title":"Universal Value Density Estimation for Imitation Learning and Goal-Conditioned Reinforcement Learning","created":"2020-02-15","cited_by_count":12},{"id":"2212.01105","title":"Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery","created":"2022-12-02","cited_by_count":12},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11},{"id":"2308.00031","title":"Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges","created":"2023-07-31","cited_by_count":10},{"id":"2502.12530","title":"Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations","created":"2025-02-18","cited_by_count":6},{"id":"2407.20299","title":"Dataset Distillation for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":5},{"id":"2408.02165","title":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","created":"2024-08-04","cited_by_count":3}],"next_cursor":null}