再励学习——原理、算法及其在智能控制中的应用

被引:11
作者
阎平凡
机构
[1] 清华大学自动化系北京
关键词
再励学习; 学习控制; 智能控制;
D O I
10.13976/j.cnki.xk.1996.01.007
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
综述了再励学习(Reinforcement Learning)的原理,主要算法,基于神经网络的实现及其在智能控制中的作用,探讨了应进一步研究的问题.
引用
收藏
页码:28 / 34+43 +43
页数:8
相关论文
共 24 条
[11]  
Refinement of Robot Motor Skills through RL. Franklin J A. Proc 27th Conference on Decision and Control . 1988
[12]  
Process Control via ANN and RL. Hoakins J C,et al. Computers in Chemical Engineering . 1992
[13]  
Genetic-Based Machine Learning and Behavior-Based Robotics:A New Synthesis. Dorigo M,et al. IEEE Trans,SMC . 1993
[14]  
Learning and Tuning Fuzzy Logic Controller through Reinforcement. Berenji H R,et al. IEEE Transactions on Neural Networks . 1992
[15]  
A Menu of Design for RL over Time. Werbos P J. Neural Networks for Robotics and Control . 1990
[16]  
Large Stochastic Systems:Learning Automata,Systems and Control Encyclopedia. Narenda K S. Theory,Technology and Applications . 1987
[17]  
Reinforcement Learning is Direct Adaptive Optimal Control. Sutton R S. IEEE Control Systems Magazine . 1992
[18]  
Sequential Decision Problems and Neural Network. Barto A G,et al. Learning and Computational Neuroscience . 1991
[19]  
Temporal Credit Assignment in Reinforcement Learning. Sutton R S. . 1984
[20]  
Associative Reinforcement Learning,Function in K-DNF. Kaelbing L P. Machine Learning . 1994