{"list":"other","total":85,"rows":[{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"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":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"1907.01657","title":"Dynamics-Aware Unsupervised Discovery of Skills","created":"2019-07-02","cited_by_count":313},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"1611.07507","title":"Variational Intrinsic Control","created":"2016-11-22","cited_by_count":267},{"id":"2301.10677","title":"Imitating Human Behaviour with Diffusion Models","created":"2023-01-25","cited_by_count":263},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139},{"id":"2402.16796","title":"Expressive Whole-Body Control for Humanoid Robots","created":"2024-02-26","cited_by_count":139},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"1912.02875","title":"Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions","created":"2019-12-05","cited_by_count":125},{"id":"2310.04582","title":"Universal Humanoid Motion Representations for Physics-Based Control","created":"2023-10-06","cited_by_count":116},{"id":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"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":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105},{"id":"2210.10047","title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","created":"2022-10-18","cited_by_count":103},{"id":"1811.11359","title":"Unsupervised Control Through Non-Parametric Discriminative Rewards","created":"2018-11-28","cited_by_count":102},{"id":"2106.05969","title":"Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation","created":"2021-06-10","cited_by_count":101},{"id":"1811.11711","title":"Neural probabilistic motor primitives for humanoid control","created":"2018-11-28","cited_by_count":97},{"id":"2305.02195","title":"CALM: Conditional Adversarial Latent Models for Directable Virtual Characters","created":"2023-05-02","cited_by_count":94},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86},{"id":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83},{"id":"2103.03236","title":"Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap","created":"2021-03-04","cited_by_count":81},{"id":"2206.01079","title":"When does return-conditioned supervised learning work for offline reinforcement learning?","created":"2022-06-02","cited_by_count":76},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71},{"id":"2101.07123","title":"Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint","created":"2021-01-18","cited_by_count":70},{"id":"2202.00161","title":"CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery","created":"2022-02-01","cited_by_count":68},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68},{"id":"2206.03023","title":"How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression","created":"2022-06-07","cited_by_count":66},{"id":"2309.01952","title":"Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperation","created":"2023-09-05","cited_by_count":54},{"id":"2008.10066","title":"Learning Off-Policy with Online Planning","created":"2020-08-23","cited_by_count":53},{"id":"2212.00541","title":"Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo","created":"2022-12-01","cited_by_count":47},{"id":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42},{"id":"2305.02968","title":"Masked Trajectory Models for Prediction, Representation, and Control","created":"2023-05-04","cited_by_count":42},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38},{"id":"2402.08848","title":"Hybrid Inverse Reinforcement Learning","created":"2024-02-13","cited_by_count":32},{"id":"2305.16985","title":"Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation","created":"2023-05-26","cited_by_count":31},{"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},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29},{"id":"2407.00187","title":"SMPLOlympics: Sports Environments for Physically Simulated Humanoids","created":"2024-06-28","cited_by_count":29},{"id":"2405.18418","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","created":"2024-05-28","cited_by_count":27},{"id":"2205.15397","title":"Minimax Optimal Online Imitation Learning via Replay Estimation","created":"2022-05-30","cited_by_count":25},{"id":"2208.07363","title":"MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control","created":"2022-08-15","cited_by_count":25},{"id":"2301.02099","title":"Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping","created":"2023-01-05","cited_by_count":25},{"id":"2209.12016","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","created":"2022-09-24","cited_by_count":21},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21},{"id":"2403.06862","title":"Real-Time Simulated Avatar from Head-Mounted Sensors","created":"2024-03-11","cited_by_count":17},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12},{"id":"2312.02682","title":"H-GAP: Humanoid Control with a Generalist Planner","created":"2023-12-05","cited_by_count":11},{"id":"2307.01938","title":"Physics-based Motion Retargeting from Sparse Inputs","created":"2023-07-04","cited_by_count":10},{"id":"2407.18178","title":"PianoMime: Learning a Generalist, Dexterous Piano Player from Internet Demonstrations","created":"2024-07-25","cited_by_count":9},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4},{"id":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","cited_by_count":4},{"id":"2210.14685","title":"Leveraging Demonstrations with Latent Space Priors","created":"2022-10-26","cited_by_count":3}],"next_cursor":null}