Reinforcement learning of fuzzy logic controllers

Сентябрь 13, 2022

Главная
Алгебра
Reinforcement learning of fuzzy logic controllers

Содержание

2. What is fuzzy logic?
3. Fuzzy Logic Simple example of the logic for temperature regulator that uses a fan might look
5. Example of rules:
10. There are three types of scheme: FLC – Fuzzy Logic Controllers NN – Neural Networks RL
11. FLC For Sony legged robots, the output action is the discrete command set, each of which
12. A reactive control scheme is employed for Sony legged robots to approach the ball in a
13. The input state vector is S = [s1, s2]T = [θ, d]T. This behavior is to
14. We define F(j, n) as the j-th fuzzy set (j=1…ln) and ln the number of fuzzy
15. Experimental results The experimental results show the FLC can be learned by the proposed reinforcement learning
17. Скачать презентацию

Слайд 2

What is fuzzy logic?

Слайд 3

Fuzzy Logic
Simple example of the logic for temperature regulator that uses

a fan might look like this:

Слайд 4

Слайд 5

Example of rules:

Слайд 6

Слайд 7

Слайд 8

Слайд 9

Слайд 10

There are three types of scheme:
FLC – Fuzzy Logic Controllers

NN – Neural Networks
RL – Reinforcement Learning

Because of small set of rules, FLC scheme is more suitable than NN or RL control schemes.

Слайд 11

FLC
For Sony legged robots, the output action is the discrete command

set, each of which can make the robot move single steps in different directions.

Слайд 12

A reactive control scheme is employed for Sony legged robots to

approach the ball in a game. There are two state variables: the orientation relative to the ball represented by θ and the distance to the ball by d, which are important for this behavior due to the lack of global co-ordination.

Слайд 13

The input state vector is S = [s1, s2]T = [θ,

d]T. This behavior is to control the robot to approach the ball by taking action such as MOVE FORWARD, LFFT FORWARD, RIGHT FORWARD, LEFT TURN, or RIGHT TURN, which are provided by low-level walking software.

Слайд 14

We define F(j, n) as the j-th fuzzy set (j=1…ln)

and ln the number of fuzzy sets for the input state variable sn. A quadruple of (a,b,c,d) is used to represent the triangle or trapezoid membership function of the fuzzy set as shown in figure 2 where b = c for triangle shape. The output action a is the crisp value that can be seen as a fuzzy singleton cm (m=1…M) in a FLC.

Слайд 15