以改良安全性增強式學習為基礎的自我適應進化演算法應用於模糊類神經控制器設計之研究

Abstract

在本篇論文中，提出了改良安全性增強式學習為基礎的自我適應進化演算法應用於TSK型式模糊類神經控制器的設計上。本論文所提出的方法可以改善增強式學習的訊號設計以及傳統的進化演算法。本論文的方法可以分為兩部份來探討。首先，在第一部份中本論文提出了自我適應進化演算法來解決傳統進化演算法所遭遇到的問題，如: 1)將所有模糊規則編碼至一條染色體中；2)模糊法則需要在學習前指定；3)無法局部考量單一模糊法則。在第二部份中，本論文提出了改良安全性增強式學習。在改良安全性增強式學習中透過兩個不同的策略-判斷以及衡量策略來決定增強式訊號。此外，Lyapunov 穩定性分析也被考量在本論文所提出的改良安全性增強式學習。在本文中提出了單桿以及雙桿倒單擺控制系統來驗證本論文所提出方法的效能，從實驗結果中可以發現，相較於其他進化演算法，本論文所提出的方法有較佳的效能。

In this dissertation, improved safe reinforcement learning based self adaptive evolutionary algorithms (ISRL-SAEAs) are proposed for TSK-type neuro-fuzzy controller design. The ISRL-SAEAs can improve not only the reinforcement signal designed but also traditional evolutionary algorithms. There are two parts in the proposed ISRL-SAEAs. In the first part, the SAEAs are proposed to solve the following problems: 1) all the fuzzy rules are encoded into one chromosome; 2) the number of fuzzy rules has to be assigned in advance; and 3) the population cannot evaluate each fuzzy rule locally. The second part of the ISRL-SAEAs is the ISRL. In the ISRL, two different strategies (judgment and evaluation) are used to design the reinforcement signal. Moreover the Lyapunov stability is considered in ISRL. To demonstrate the performance of the proposed method, the inverted pendulum control system and tandem pendulum control system are presented. As shown in simulation, the ISRL-SAEAs perform better than other reinforcement evolution methods.