{"list":"other","total":54,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"1809.02925","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","created":"2018-09-09","cited_by_count":204},{"id":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193},{"id":"2306.00958","title":"LIV: Language-Image Representations and Rewards for Robotic Control","created":"2023-06-01","cited_by_count":188},{"id":"1807.06158","title":"Generative Adversarial Imitation from Observation","created":"2018-07-17","cited_by_count":184},{"id":"2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","created":"2023-10-12","cited_by_count":164},{"id":"1609.07088","title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","created":"2016-09-22","cited_by_count":127},{"id":"2109.13333","title":"Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients","created":"2021-09-27","cited_by_count":122},{"id":"2312.10812","title":"Learning to Act without Actions","created":"2023-12-17","cited_by_count":121},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108},{"id":"2105.06411","title":"Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration","created":"2021-05-13","cited_by_count":93},{"id":"2011.06507","title":"Reinforcement Learning with Videos: Combining Offline Observations with Interaction","created":"2020-11-12","cited_by_count":82},{"id":"2210.05178","title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","created":"2022-10-11","cited_by_count":78},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78},{"id":"2102.13185","title":"Off-Policy Imitation Learning from Observations","created":"2021-02-25","cited_by_count":70},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68},{"id":"1906.08113","title":"Wasserstein Adversarial Imitation Learning","created":"2019-06-19","cited_by_count":60},{"id":"2007.14189","title":"TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning","created":"2020-07-28","cited_by_count":47},{"id":"1910.04417","title":"Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement","created":"2019-10-10","cited_by_count":46},{"id":"2201.11972","title":"DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs","created":"2022-01-28","cited_by_count":43},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42},{"id":"1709.06683","title":"OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning","created":"2017-09-20","cited_by_count":40},{"id":"1603.06348","title":"Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstration","created":"2016-03-21","cited_by_count":36},{"id":"2211.11972","title":"imitation: Clean Imitation Learning Implementations","created":"2022-11-22","cited_by_count":34},{"id":"2309.13041","title":"Robotic Offline RL from Internet Videos via Value-Function Pre-Training","created":"2023-09-22","cited_by_count":33},{"id":"2008.09167","title":"Imitation Learning with Sinkhorn Distances","created":"2020-08-20","cited_by_count":30},{"id":"2006.13258","title":"Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization","created":"2020-06-23","cited_by_count":22},{"id":"1803.05402","title":"Imitation Learning with Concurrent Actions in 3D Games","created":"2018-03-14","cited_by_count":18},{"id":"2201.01448","title":"Conditional Imitation Learning for Multi-Agent Games","created":"2022-01-05","cited_by_count":13},{"id":"2203.02214","title":"Plan Your Target and Learn Your Skills: Transferable State-Only Imitation Learning via Decoupled Policy Optimization","created":"2022-03-04","cited_by_count":12},{"id":"2010.04767","title":"Robust Behavioral Cloning for Autonomous Vehicles using End-to-End Imitation Learning","created":"2020-10-09","cited_by_count":11},{"id":"2312.02019","title":"Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models","created":"2023-12-04","cited_by_count":5}],"next_cursor":null}