查詢結果分析
來源資料
相關文獻
- A GA-based Adaptive Fuzzy System with Reinforcement Learning
- Reinforcement Learning for Ga-Based Neural Networks
- Learning to Predict Temperature and Time-Series by Using Neural Fuzzy Systems
- 結合演化算法於模糊系統及其效率之分析與比較
- Hybrid Genetic Algorithm/Fuzzy System, Simulated Annealing and Tabu Search for Short-Term Thermal Generating Unit Commitment
- 都市計畫草圖替選方案分析模式之實例研究
- 運用類神經網路於股價指數之套利--以日經225指數為例
- 二次元靜態連續體結構之最佳化:應用族群概念之基因演算法
- 遺傳基因演算法在彈性製造系統排程問題之探討
- 適應性突變運算及其運用
頁籤選單縮合
題名 | A GA-based Adaptive Fuzzy System with Reinforcement Learning=以基因演算法為基礎之適應性模糊系統具有加強式學習能力 |
---|---|
作者姓名(中文) | 林正堅; | 書刊名 | 朝陽學報 |
卷期 | 6 2001.06[民90.06] |
頁次 | 頁91-112 |
分類號 | 448.942 |
關鍵詞 | 模糊系統; 基因演算法; 加強式學習; Fuzzy system; GA; Reinforcement learning; |
語文 | 英文(English) |
中文摘要 | 本篇論文描述以基因演算法為基礎之適應性模糊系統來解決各種加強式學習問題,所提出GAAFS模型為順向多層網路,其結合模糊控制器的函數成為連結架構。在基因演算法中,來自於外界環境的加強式訊號被用來當作適合函數。透過電腦模擬驗證證本系統具較佳效能。 |
英文摘要 | This paper describes a GA-Based Adaptive Fuzzy System (GAAFS) for solving various reinforcement learning problems. The proposed GAAFS is a feedforward multilayer network that integrates the basic elements and functions of a traditional fuzzy controller into a connectionist structure. The reinforcement signal from the environment is used as a fitness function for the GA-based learning of the multilayer network. That is, we formulate a number of time steps before failure occurs as the fitness function of the GA. Computer simulations have been conducted to illustrate the performance of the proposed model. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。