{"list":"other","total":66,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"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":"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":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"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":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2211.01095","title":"DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models","created":"2022-11-02","cited_by_count":938},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"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":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"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":"2207.07601","title":"ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning","created":"2022-07-15","cited_by_count":368},{"id":"2201.06503","title":"Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models","created":"2022-01-17","cited_by_count":334},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302},{"id":"2206.09012","title":"Diffusion models as plug-and-play priors","created":"2022-06-17","cited_by_count":231},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212},{"id":"2209.14548","title":"Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling","created":"2022-09-29","cited_by_count":182},{"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":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112},{"id":"2206.07309","title":"Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models","created":"2022-06-15","cited_by_count":83},{"id":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83},{"id":"2312.00852","title":"Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion","created":"2023-12-01","cited_by_count":78},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57},{"id":"2207.02200","title":"Offline RL Policies Should be Trained to be Adaptive","created":"2022-07-05","cited_by_count":52},{"id":"2307.15042","title":"TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis","created":"2023-07-27","cited_by_count":49},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48},{"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":"2206.08569","title":"Bootstrapped Transformer for Offline Reinforcement Learning","created":"2022-06-17","cited_by_count":37},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36},{"id":"2401.02015","title":"Improving Diffusion-Based Image Synthesis with Context Prediction","created":"2024-01-04","cited_by_count":32},{"id":"2405.17098","title":"Q-value Regularized Transformer for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":29},{"id":"2405.20692","title":"In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought","created":"2024-05-31","cited_by_count":26},{"id":"2406.00079","title":"Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling","created":"2024-05-31","cited_by_count":18},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13},{"id":"2303.14716","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","created":"2023-03-26","cited_by_count":12},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","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":"2405.12094","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","created":"2024-05-20","cited_by_count":7},{"id":"2210.07636","title":"Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning","created":"2022-10-14","cited_by_count":6},{"id":"2410.15698","title":"Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces","created":"2024-10-21","cited_by_count":6},{"id":"2411.01168","title":"Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization","created":"2024-11-02","cited_by_count":6},{"id":"2407.20299","title":"Dataset Distillation for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":5},{"id":"2310.05086","title":"Learning Generalizable Agents via Saliency-Guided Features Decorrelation","created":"2023-10-08","cited_by_count":4},{"id":"2408.02165","title":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","created":"2024-08-04","cited_by_count":3}],"next_cursor":null}