Xi Chen, Ali Ghadirzadeh, Tianhe Yu, Jianhao Wang, Alex Yuan Gao, Wenzhe Li, Liang Bin, Chelsea Finn, Chongjie Zhang. LAPO: Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022. 2022. [doi]
@inproceedings{ChenGYWGLBFZ22,
title = {LAPO: Latent-Variable Advantage-Weighted Policy Optimization for Offline Reinforcement Learning},
author = {Xi Chen and Ali Ghadirzadeh and Tianhe Yu and Jianhao Wang and Alex Yuan Gao and Wenzhe Li and Liang Bin and Chelsea Finn and Chongjie Zhang},
year = {2022},
url = {http://papers.nips.cc/paper_files/paper/2022/hash/efb2072a358cefb75886a315a6fcf880-Abstract-Conference.html},
researchr = {https://researchr.org/publication/ChenGYWGLBFZ22},
cites = {0},
citedby = {0},
booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022},
editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh},
isbn = {9781713871088},
}