Prati
Xue Bin Peng
Xue Bin Peng
Assistant Professor, Simon Fraser University, NVIDIA
Potvrđena adresa e-pošte na sfu.ca - Početna stranica
Naslov
Citirano
Citirano
Godina
Sim-to-real transfer of robotic control with dynamics randomization
XB Peng, M Andrychowicz, W Zaremba, P Abbeel
2018 IEEE international conference on robotics and automation (ICRA), 3803-3810, 2018
12942018
Deepmimic: Example-guided deep reinforcement learning of physics-based character skills
XB Peng, P Abbeel, S Levine, M Van de Panne
ACM Transactions On Graphics (TOG) 37 (4), 1-14, 2018
9252018
Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning
XB Peng, G Berseth, KK Yin, M Van De Panne
ACM Transactions on Graphics (TOG) 36 (4), 1-13, 2017
5992017
Learning agile robotic locomotion skills by imitating animals
XB Peng, E Coumans, T Zhang, TW Lee, J Tan, S Levine
arXiv preprint arXiv:2004.00784, 2020
3872020
Advantage-weighted regression: Simple and scalable off-policy reinforcement learning
XB Peng, A Kumar, G Zhang, S Levine
arXiv preprint arXiv:1910.00177, 2019
3272019
Terrain-adaptive locomotion skills using deep reinforcement learning
XB Peng, G Berseth, M Van de Panne
ACM Transactions on Graphics (TOG) 35 (4), 1-12, 2016
3062016
2018 IEEE international conference on robotics and automation (ICRA)
XB Peng, M Andrychowicz, W Zaremba, P Abbeel
2452018
Sfv: Reinforcement learning of physical skills from videos
XB Peng, A Kanazawa, J Malik, P Abbeel, S Levine
ACM Transactions On Graphics (TOG) 37 (6), 1-14, 2018
2252018
Variational discriminator bottleneck: Improving imitation learning, inverse rl, and gans by constraining information flow
XB Peng, A Kanazawa, S Toyer, P Abbeel, S Levine
arXiv preprint arXiv:1810.00821, 2018
2162018
AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
XB Peng, Z Ma, P Abbeel, S Levine, A Kanazawa
ACM Transactions on Graphics (TOG) 40 (4), 1-20, 2021
1882021
Mcp: Learning composable hierarchical control with multiplicative compositional policies
XB Peng, M Chang, G Zhang, P Abbeel, S Levine
Advances in Neural Information Processing Systems 32, 2019
1832019
Learning locomotion skills using deeprl: Does the choice of action space matter?
XB Peng, M Van De Panne
Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation …, 2017
1752017
Reinforcement learning for robust parameterized locomotion control of bipedal robots
Z Li, X Cheng, XB Peng, P Abbeel, S Levine, G Berseth, K Sreenath
2021 IEEE International Conference on Robotics and Automation (ICRA), 2811-2817, 2021
1632021
Ase: Large-scale reusable adversarial skill embeddings for physically simulated characters
XB Peng, Y Guo, L Halper, S Levine, S Fidler
ACM Transactions On Graphics (TOG) 41 (4), 1-17, 2022
882022
Dynamic terrain traversal skills using reinforcement learning
XB Peng, G Berseth, M Van de Panne
ACM Transactions on Graphics (TOG) 34 (4), 1-11, 2015
882015
Deep reinforcement learning for modeling human locomotion control in neuromechanical simulation
S Song, Ł Kidziński, XB Peng, C Ong, J Hicks, S Levine, CG Atkeson, ...
Journal of neuroengineering and rehabilitation 18, 1-17, 2021
762021
Offline meta-reinforcement learning with advantage weighting
E Mitchell, R Rafailov, XB Peng, S Levine, C Finn
International Conference on Machine Learning, 7780-7791, 2021
722021
Reward-conditioned policies
A Kumar, XB Peng, S Levine
arXiv preprint arXiv:1912.13465, 2019
672019
Legged robots that keep on learning: Fine-tuning locomotion policies in the real world
L Smith, JC Kew, XB Peng, S Ha, J Tan, S Levine
2022 International Conference on Robotics and Automation (ICRA), 1593-1599, 2022
632022
On learning symmetric locomotion
F Abdolhosseini, HY Ling, Z Xie, XB Peng, M Van de Panne
Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and …, 2019
512019
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20