Russ Tedrake, Teresa Weirui Zhang, H. Sebastian Seung. Stochastic policy gradient reinforcement learning on a simple 3D biped. In 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28 - October 2, 2004. pages 2849-2854, IEEE, 2004. [doi]
@inproceedings{TedrakeZS04,
title = {Stochastic policy gradient reinforcement learning on a simple 3D biped},
author = {Russ Tedrake and Teresa Weirui Zhang and H. Sebastian Seung},
year = {2004},
doi = {10.1109/IROS.2004.1389841},
url = {http://dx.doi.org/10.1109/IROS.2004.1389841},
researchr = {https://researchr.org/publication/TedrakeZS04},
cites = {0},
citedby = {0},
pages = {2849-2854},
booktitle = {2004 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sendai, Japan, September 28 - October 2, 2004},
publisher = {IEEE},
isbn = {0-7803-8463-6},
}