Please use this identifier to cite or link to this item:
標題: Reinforcement Interval Type-2 Fuzzy Controller Design by Online Rule Generation and Q-Value-Aided Ant Colony Optimization
作者: Juang, C.F.
Hsu, C.H.
關鍵字: Ant colony optimization (ACO);fuzzy Q-learning;interval type-2 fuzzy;sets;reinforcement learning;type-2 fuzzy systems;neural-network;logic systems;fpga implementation;symbiotic evolution;inference network;interpretability;algorithm;robots
Project: Ieee Transactions on Systems Man and Cybernetics Part B-Cybernetics
期刊/報告no:: Ieee Transactions on Systems Man and Cybernetics Part B-Cybernetics, Volume 39, Issue 6, Page(s) 1528-1542.
This paper proposes a new reinforcement-learning method using online rule generation and Q-value-aided ant colony optimization (ORGQACO) for fuzzy controller design. The fuzzy controller is based on an interval type-2 fuzzy system (IT2FS). The antecedent part in the designed IT2FS uses interval type-2 fuzzy sets to improve controller robustness to noise. There are initially no fuzzy rules in the IT2FS. The ORGQACO concurrently designs both the structure and parameters of an IT2FS. We propose an online interval type-2 rule generation method for the evolution of system structure and flexible partitioning of the input space. Consequent part parameters in an IT2FS are designed using Q-values and the reinforcement local-global ant colony optimization algorithm. This algorithm selects the consequent part from a set of candidate actions according to ant pheromone trails and Q-values, both of which are updated using reinforcement signals. The ORGQACO design method is applied to the following three control problems: 1) truck-backing control; 2) magnetic-levitation control; and 3) chaotic-system control. The ORGQACO is compared with other reinforcement-learning methods to verify its efficiency and effectiveness. Comparisons with type-1 fuzzy systems verify the noise robustness property of using an IT2FS.
ISSN: 1083-4419
DOI: 10.1109/tsmcb.2009.2020569
Appears in Collections:電機工程學系所

Show full item record

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.