Cooperative Q-learning based on learning automata

The theory of learning automata has already been applied in reinforcement learning which is characterized by single-agent and single-stage. This paper proposed a multi-robot cooperative Q-learning algorithm based on learning automata. Each robot updates probability for action selection through the l...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2009 IEEE International Conference on Automation and Logistics s. 1973 - 1978
Hlavní autori: Mao Yang, Yantao Tian, Xinyue Qi
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.08.2009
Predmet:
Communication system control
Informatics
Learning automata
Mobile robots
multi-robot reinforcement learning
Network servers
Neural networks
Q-learning
Radio communication
Robot control
Robot sensing systems
Robotics and automation
ISBN:9781424447947, 1424447941
ISSN:2161-8151
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The theory of learning automata has already been applied in reinforcement learning which is characterized by single-agent and single-stage. This paper proposed a multi-robot cooperative Q-learning algorithm based on learning automata. Each robot updates probability for action selection through the learning automata constantly, and then converts the probability to special experience. Robots can accelerate the learning process by means of sharing experiences among each other. Simulation experiments verify the effectiveness of this algorithm.
ISBN:9781424447947
1424447941
ISSN:2161-8151
DOI:10.1109/ICAL.2009.5262629