Embedding fuzzy mechanisms and knowledge in box-type reinforcement learning controllers

Shun-Feng Su1, Sheng-Hsiung Hsieh1
1National Taiwan University of Science and Technology, Taipei, Taiwan

Tóm tắt

In this paper, we report our study on embedding fuzzy mechanisms and knowledge into box-type reinforcement learning controllers. One previous approach for incorporating fuzzy mechanisms can only achieve one successful run out of nine tests compared to eight successful runs in a nonfuzzy learning control scheme. After analysis, the credit assignment problem and the weighting domination problem are identified. Furthermore, the use of fuzzy mechanisms in temporal difference seems to play a negative factor. Modifications to overcome those problems are proposed. Furthermore, several remedies are employed in that approach. The effects of those remedies applied to our learning scheme are presented and possible variations are also studied. Finally, the issue of incorporating knowledge into reinforcement learning systems is studied. From our simulations, it is concluded that the use of knowledge for the control network can provide good learning results, but the use of knowledge for the evaluation network alone seems unable to provide any significant advantages. Furthermore, we also employ Makarovic's (1988) rules as the knowledge for the initial setting of the control network. In our study, the rules are separated into four groups to avoid the ordering problem.

Từ khóa

#Fuzzy control #Supervised learning #Control systems #Unsupervised learning #System performance #Testing #Learning systems #Control system synthesis #Neural networks #Fuzzy systems

Tài liệu tham khảo

10.1109/91.273126 10.1109/72.159061 10.1109/ICSMC.1999.816639 schoknecht, 1999, using reinforcement learning for engine control, Proceedings of 9th International Conference on Artificial Neural Networks ICANN 99, 1, 329, 10.1049/cp:19991130 10.1109/IJCNN.1999.833414 10.1109/ICIT.2000.854247 10.1109/3477.836376 10.1007/BF00115009 hsieh, 1997, On the study of embedding fuzzy concept and prior knowledge in reinforcement learning kim, 1995, Analysis and study of neural-networks-based reinforcement learning 10.1109/TAC.1965.1098193 10.1109/JRPROC.1961.287775 10.1109/TSMC.1983.6313077 10.1147/rd.33.0210 10.1002/int.4550060105 10.1109/37.24809 lin, 1996, Neural Fuzzy System A Neuro-Fuzzy Synergism to Intelligent Systems kokar, 1992, learning control methods, needs, and architectures, An Introduction to Intelligent and Autonomous Control 10.1080/02533839.2001.9670633 10.1109/TSMC.1985.6313399 yager, 1994, Essentials of Fuzzy Modeling and Control 10.1109/FUZZY.1992.258745 10.1109/21.97472 10.1109/TAC.1997.633847 makarovic, 1988, A qualitative way of solving the pole balancing problem