| Mopo: Model-based offline policy optimization T Yu, G Thomas, L Yu, S Ermon, JY Zou, S Levine, C Finn, T Ma Advances in Neural Information Processing Systems 33, 14129-14142, 2020 | 899 | 2020 |
| Value iteration networks A Tamar, Y Wu, G Thomas, S Levine, P Abbeel Advances in neural information processing systems 29, 2016 | 788 | 2016 |
| Learning robotic assembly from cad G Thomas, M Chien, A Tamar, JA Ojea, P Abbeel 2018 IEEE International Conference on Robotics and Automation (ICRA), 3524-3531, 2018 | 194 | 2018 |
| Safe reinforcement learning by imagining the near future G Thomas, Y Luo, T Ma Advances in Neural Information Processing Systems 34, 13859-13869, 2021 | 84 | 2021 |
| Learning from the hindsight plan—episodic mpc improvement A Tamar, G Thomas, T Zhang, S Levine, P Abbeel 2017 IEEE International Conference on Robotics and Automation (ICRA), 336-343, 2017 | 82 | 2017 |
| Model-based adversarial meta-reinforcement learning Z Lin, G Thomas, G Yang, T Ma Advances in Neural Information Processing Systems 33, 10161-10173, 2020 | 60 | 2020 |
| A model-based approach for sample-efficient multi-task reinforcement learning NC Landolfi, G Thomas, T Ma arXiv preprint arXiv:1907.04964, 2019 | 19 | 2019 |
| A comprehensive guide to machine learning S Nasiriany, G Thomas, W Wang, A Yang, J Listgarten, A Sahai Department of Electrical Engineering and Computer Sciences University of …, 2019 | 17 | 2019 |
| Plex: Making the most of the available data for robotic manipulation pretraining G Thomas, CA Cheng, R Loynd, FV Frujeri, V Vineet, M Jalobeanu, ... Conference on Robot Learning, 2624-2641, 2023 | 10 | 2023 |
| Mathematics for Machine Learning G Thomas University of California, Berkeley, 2018 | 2 | 2018 |
| HEETR: Pretraining for Robotic Manipulation on Heteromodal Data G Thomas, A Kolobov, CA Cheng, V Vineet, M Jalobeanu CoRL 2022 Workshop on Pre-training Robot Learning, 0 | | |
Sergey LevineUC Berkeley, Physical IntelligenceEmail verificata su eecs.berkeley.edu