Yunfei Zhang, Weilin Li, Clarence W. de Silva. Rsmdp-Based robust Q-Learning for Optimal Path Planning in a Dynamic Environment. I. J. Robotics and Automation, 31(4), 2016. [doi]
@article{ZhangLS16-2,
title = {Rsmdp-Based robust Q-Learning for Optimal Path Planning in a Dynamic Environment},
author = {Yunfei Zhang and Weilin Li and Clarence W. de Silva},
year = {2016},
doi = {10.2316/Journal.206.2016.4.206-4255},
url = {http://dx.doi.org/10.2316/Journal.206.2016.4.206-4255},
researchr = {https://researchr.org/publication/ZhangLS16-2},
cites = {0},
citedby = {0},
journal = {I. J. Robotics and Automation},
volume = {31},
number = {4},
}