Trajectory Sampling Value Iteration: Improved Dyna Search for MDPs

Yicheng Zhou, Quan Liu, Qi-ming Fu, Zongzhang Zhang. Trajectory Sampling Value Iteration: Improved Dyna Search for MDPs. In Gerhard Weiss, Pinar Yolum, Rafael H. Bordini, Edith Elkind, editors, Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2015, Istanbul, Turkey, May 4-8, 2015. pages 1685-1686, ACM, 2015. [doi]

Authors

Yicheng Zhou

This author has not been identified. Look up 'Yicheng Zhou' in Google

Quan Liu

This author has not been identified. Look up 'Quan Liu' in Google

Qi-ming Fu

This author has not been identified. Look up 'Qi-ming Fu' in Google

Zongzhang Zhang

This author has not been identified. Look up 'Zongzhang Zhang' in Google