{"list":"other","total":63,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"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":"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":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"1910.11215","title":"RoboNet: Large-Scale Multi-Robot Learning","created":"2019-10-24","cited_by_count":270},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238},{"id":"1812.00568","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","created":"2018-12-03","cited_by_count":230},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","cited_by_count":153},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"1509.01149","title":"Model Predictive Path Integral Control using Covariance Variable Importance Sampling","created":"2015-09-03","cited_by_count":124},{"id":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105},{"id":"2009.06799","title":"The Importance of Pessimism in Fixed-Dataset Policy Optimization","created":"2020-09-15","cited_by_count":99},{"id":"2201.13425","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","created":"2022-01-31","cited_by_count":96},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94},{"id":"1810.04586","title":"The Laplacian in RL: Learning Representations with Efficient Approximations","created":"2018-10-10","cited_by_count":86},{"id":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83},{"id":"2006.13205","title":"Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors","created":"2020-06-23","cited_by_count":62},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62},{"id":"2402.11337","title":"Learning by Reconstruction Produces Uninformative Features For Perception","created":"2024-02-17","cited_by_count":55},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47},{"id":"2007.07170","title":"Goal-Aware Prediction: Learning to Model What Matters","created":"2020-07-14","cited_by_count":45},{"id":"1710.05373","title":"Robust Locally-Linear Controllable Embedding","created":"2017-10-15","cited_by_count":38},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36},{"id":"2004.08763","title":"Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization","created":"2020-04-19","cited_by_count":32},{"id":"2407.03475","title":"How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks","created":"2024-07-03","cited_by_count":31},{"id":"2211.10831","title":"Joint Embedding Predictive Architectures Focus on Slow Features","created":"2022-11-20","cited_by_count":30},{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27},{"id":"1806.09655","title":"Learning what you can do before doing anything","created":"2018-06-25","cited_by_count":26},{"id":"2107.05545","title":"Towards Better Laplacian Representation in Reinforcement Learning with Generalized Graph Drawing","created":"2021-07-12","cited_by_count":23},{"id":"1911.05071","title":"Experience-Embedded Visual Foresight","created":"2019-11-12","cited_by_count":21},{"id":"2003.01086","title":"Predictive Coding for Locally-Linear Control","created":"2020-03-02","cited_by_count":17},{"id":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11},{"id":"2210.13153","title":"Reachability-Aware Laplacian Representation in Reinforcement Learning","created":"2022-10-24","cited_by_count":10},{"id":"2302.13493","title":"The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning","created":"2023-02-27","cited_by_count":10}],"next_cursor":null}