@inproceedings{5d150698b7ea44cc85fe5a0f9775593b,
title = "An improved reinforcement Q-learning method with BP neural networks in robot soccer",
abstract = "In traditional reinforcement Q-Learning method, there exists two problems: difficulty of dividing the state information, complexity of extreme large dimension input. To solve these two problems, this paper proposed an improved reinforcement Q-Learning method with BP neutral network. In this method, the large Q table is replaced by a BP neural network. Continuous environmental information is the input. The Q value is the output. The Q value and weight of the network are also adjusted by the action rewards. This paper presents an algorithm for single agent's action selection. Simulation shows proposed method is more stable and applicable for the agent's strategy selection.",
keywords = "BP Neural Networks, Reinforcement Q-Learning, Robot Soccer",
author = "Wang, {Shi Chao} and Song, {Zheng Xi} and Hao Ding and Shi, {Hao Bin}",
year = "2011",
doi = "10.1109/ISCID.2011.53",
language = "英语",
isbn = "9780769545004",
series = "Proceedings - 2011 4th International Symposium on Computational Intelligence and Design, ISCID 2011",
pages = "177--180",
booktitle = "Proceedings - 2011 4th International Symposium on Computational Intelligence and Design, ISCID 2011",
note = "2011 4th International Symposium on Computational Intelligence and Design, ISCID 2011 ; Conference date: 28-10-2011 Through 30-10-2011",
}