11th International Conference on Knowledge-Based Intelligent Informational and Engineering Systems/17th Italian Workshop on Neural Networks Vietri sul Mare, ITALY, SEP 12-14, 2007, Date: 2007/09/12 - 2007/09/14, Location: ITALY, Vietri sul Mare
Knowledge-Based Intelligent Information and Engineering Systems: KES 2007 - WIRN 2007, Pt III, Proceedings
Author:
Keywords:
mmdp, learning automata, optimal convergence, multi-agent reinforcement learning, Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, Cybernetics, Engineering, Electrical & Electronic, Robotics, Imaging Science & Photographic Technology, Computer Science, Engineering, MMDP
Abstract:
Learning Automata (LA) were recently shown to be valuable tools for designing Multi-Agent Reinforcement Learning algorithms. One of the principal contributions of LA theory is that a set of decentralized, independent learning automata is able to control a finite Markov Chain with unknown transition probabilities and rewards. We extend this result to the framework of Multi-Agent MDP's, a straightforward extension of single-agent MDP's to distributed cooperative multi-agent decision problems. Furthermore, we combine this result with the application of parametrized learning automata yielding global optimal convergence results.