Haoyu Ma - Google znalac

Izradite svoj profil

Citirano

	Sve	Od 2019.
Citati	10	10
H-indeks	1	1
i10-indeks	0	0

0

6

3

202320244 6

Suautori

Mingsheng LongAssociate Professor, Tsinghua UniversityPotvrđena adresa e-pošte na tsinghua.edu.cn
Jialong WuPh.D. student, Tsinghua UniversityPotvrđena adresa e-pošte na mails.tsinghua.edu.cn
Jianmin WangSchool of Software, Tsinghua UniversityPotvrđena adresa e-pošte na tsinghua.edu.cn
Zhi KouTsinghua UniversityPotvrđena adresa e-pošte na mails.tsinghua.edu.cn
Ximei WangTencent; Tsinghua UniversityPotvrđena adresa e-pošte na mails.tsinghua.edu.cn

Haoyu Ma

Haoyu Ma

Ostala imena浩宇马

Tsinghua University

Potvrđena adresa e-pošte na mails.tsinghua.edu.cn

Reinforcement Learning World Models Deep Learning


Naslov Poredaj po navodima Poredaj po godini Poredaj po naslovu	Citirano Citirano	Godina
Pre-training contextualized world models with in-the-wild videos for reinforcement learning J Wu, H Ma, C Deng, M Long Advances in Neural Information Processing Systems 36, 2024	8	2024
Harmony World Models: Boosting Sample Efficiency for Model-based Reinforcement Learning H Ma, J Wu, N Feng, J Wang, M Long arXiv preprint arXiv:2310.00344, 2023	1	2023
Bi-tuning: Efficient Transfer from Pre-trained Models J Zhong, H Ma, X Wang, Z Kou, M Long Joint European Conference on Machine Learning and Knowledge Discovery in …, 2023	1	2023

Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.

Članci 1–3