Tuning Scaling Factors of Fuzzy Logic Controllers via Reinforcement Learning Policy Gradient Algorithms
| Autor: | Ahmet Onat, Vahid Tavakol Aghaei |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Neuro-fuzzy 02 engineering and technology Fuzzy control system Defuzzification Fuzzy logic 020901 industrial engineering & automation Control theory 0202 electrical engineering electronic engineering information engineering Fuzzy number Reinforcement learning Fuzzy set operations 020201 artificial intelligence & image processing Fuzzy associative matrix Algorithm Mathematics |
| Zdroj: | ICMRE |
| DOI: | 10.1145/3068796.3068827 |
| Popis: | In this study a gain scheduling method for the scaling factors of the input variables to the fuzzy logic controller by means of policy gradient reinforcement learning algorithms has been proposed. The motivation for using PG algorithms is that they can scale RL problems into continuous high dimensional state-action spaces without the need for function approximation methods. Without incorporating any a-priori knowledge of the plant, the proposed method optimizes the cost function of the learning algorithm and tries to find optimal solutions for the scaling factors of the fuzzy logic controller. To show the effectiveness of the proposed method it has been applied to a PD type fuzzy controller along with a nonlinear model of an inverted pendulum. By performing different simulations, it is observed that the proposed method can find optimal solutions within a small number of learning iterations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|