Modeling reward functions for incomplete state representations via echo state networks

被引：21

作者：

Bush, K ^{[1
]}

Anderson, C ^{[1
]}

机构：

[1] Colorado State Univ, Dept Comp Sci, Ft Collins, CO 80523 USA

来源：

Proceedings of the International Joint Conference on Neural Networks (IJCNN), Vols 1-5 | 2005年

关键词：

D O I：

10.1109/IJCNN.2005.1556402

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

引用

页码：2995 / 3000

页数：6

共 12 条

[1] [Anonymous], 2001, ECHO STATE APPROACH
[2] Jaeger Herbert, 2002, TUTORIAL TRAINING RE, V5
[3] Kretchmar R. M., 2000, THESIS COLORADO STAT
[4] Real-time computing without stable states:: A new framework for neural computation based on perturbations
Maass, W
Natschläger, T
Markram, H
[J]. NEURAL COMPUTATION, 2002, 14 (11) : 2531 - 2560
[5] Mizutani E., 2004, P IEEE INNS INT JOIN
[6] MIZUTANI E, 2003, P IEEE INT INT S COM
[7] PLOGER P, 2003, P ROBOCUP 2003
[8] Prokhorov D. V., 2004, HDB LEARNING APPROXI, P381
[9] Sutton R. S., 1998, Reinforcement Learning: An Introduction, V22447
[10] VREEKEN J, 2004, REAL WORLD TEMPORAL