Obserwuj
Marvin Zhang
Marvin Zhang
Zweryfikowany adres z eecs.berkeley.edu - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
When to trust your model: Model-based policy optimization
M Janner, J Fu, M Zhang, S Levine
Advances in Neural Information Processing Systems (NeurIPS), 2019
4822019
Wilds: A benchmark of in-the-wild distribution shifts
PW Koh, S Sagawa, H Marklund, SM Xie, M Zhang, A Balsubramani, ...
International Conference on Machine Learning, 5637-5664, 2021
4582021
Solar: Deep structured representations for model-based reinforcement learning
M Zhang, S Vikram, L Smith, P Abbeel, M Johnson, S Levine
International Conference on Machine Learning, 7444-7453, 2019
2042019
Combining model-based and model-free updates for trajectory-centric reinforcement learning
Y Chebotar, K Hausman, M Zhang, G Sukhatme, S Schaal, S Levine
International conference on machine learning, 703-711, 2017
1682017
Deep reinforcement learning for tensegrity robot locomotion
M Zhang, X Geng, J Bruce, K Caluwaerts, M Vespignani, V SunSpiral, ...
2017 IEEE International Conference on Robotics and Automation (ICRA), 634-641, 2017
107*2017
Adaptive risk minimization: Learning to adapt to domain shift
M Zhang, H Marklund, N Dhawan, A Gupta, S Levine, C Finn
Advances in Neural Information Processing Systems 34, 23664-23678, 2021
93*2021
Learning deep neural network policies with continuous memory states
M Zhang, Z McCarthy, C Finn, S Levine, P Abbeel
2016 IEEE international conference on robotics and automation (ICRA), 520-527, 2016
792016
Avid: Learning multi-stage tasks via pixel-level translation of human videos
L Smith, N Dhawan, M Zhang, P Abbeel, S Levine
Robotics: Science and Systems (RSS), 2019
692019
Memo: Test time robustness via adaptation and augmentation
M Zhang, S Levine, C Finn
arXiv preprint arXiv:2110.09506, 2021
262021
Guided policy search code implementation, 2016
C Finn, M Zhang, J Fu, X Tan, Z McCarthy, E Scharff, S Levine
Software available from rll. berkeley. edu/gps, 2016
242016
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–10