Следене
Haoqi Yuan
Haoqi Yuan
Потвърден имейл адрес: pku.edu.cn
Заглавие
Позовавания
Позовавания
Година
Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks
H Yuan, C Zhang, H Wang, F Xie, P Cai, H Dong, Z Lu
NeurIPS 2023 Foundation Models for Decision Making Workshop, 2023
40*2023
Robust task representations for offline meta-reinforcement learning via contrastive learning
H Yuan, Z Lu
International Conference on Machine Learning, 25747-25759, 2022
212022
DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos
H Yuan, R Wu, A Zhao, H Zhang, Z Ding, H Dong
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2021
22021
Creative agents: Empowering agents with imagination for creative tasks
C Zhang, P Cai, Y Fu, H Yuan, Z Lu
arXiv preprint arXiv:2312.02519, 2023
12023
DLGAN: disentangling label-specific fine-grained features for image manipulation
G Zhan, Y Zhao, B Zhao, H Yuan, B Chen, H Dong
arXiv preprint arXiv:1911.09943, 2019
12019
Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning
H Yuan, Z Mu, F Xie, Z Lu
International Conference on Learning Representations, 2024
2024
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–6