Volume 8, Issue 1 (Journal of Control, V.8, N.1 Spring 2014)
JoC 2014, 8(1): 11-20 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Ghorbani F, Derhami V, NezamAbadi pour H. A Novel approach in Fuzzy Reinforcement Learning . JoC 2014; 8 (1) :11-20
URL: http://joc.kntu.ac.ir/article-1-35-en.html
URL: http://joc.kntu.ac.ir/article-1-35-en.html
1- Yazd University
2- university of Kerman
2- university of Kerman
Abstract: (11548 Views)
In this paper, we present a novel continuous reinforcement learning approach. The proposed approach, called "Fuzzy Least Squares Policy Iteration (FLSPI)", is obtained from combination of "Least Squares Policy Iteration (LSPI)" and a zero order Takagi Sugeno fuzzy system. We define state-action basis function based on fuzzy system so that LSPI conditions are satisfied. It is proven that there is an error bound for difference of the exact state-action value function and approximated state-action value function obtained by FLSPI. Simulation results show that learning speed and operation quality for FLSPI are higher than two previous critic-only fuzzy reinforcement learning approaches i.e. fuzzy Q-learning and fuzzy Sarsa learning. Another advantage of this approach is needlessness to learning rate determination.
Keywords: Reinforcement learning, least square policy iteration, state-action function approximation, fuzzy system
Type of Article: Research paper |
Subject:
Special
Received: 2014/05/3 | Accepted: 2014/08/30 | Published: 2014/12/11
Received: 2014/05/3 | Accepted: 2014/08/30 | Published: 2014/12/11
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
