A Hybrid Multiagent Reinforcement Learning Approach using Strategies and Fusion

I. Partalas, I. Feneris, I. Vlahavas, “A Hybrid Multiagent Reinforcement Learning Approach using Strategies and Fusion”, International Journal of Artificial Intelligence Tools (IJAIT), World Scientific, 17 (5), pp. 945-961, 2008.

You are here: Home » Publications » A Hybrid Multiagent Reinforcement Learning Approach using Strategies and Fusion

Author(s): I. Partalas, I. Feneris, I. Vlahavas

Availability:

Appeared In: International Journal of Artificial Intelligence Tools (IJAIT), World Scientific, 17 (5), pp. 945-961, 2008.

Keywords: multi-agent reinforcement learning.

Tags:

2008, Feneris, Partalas, Vlahavas

Abstract: Reinforcement Learning comprises an attractive solution to the problem of coordinating a group of agents in a Multiagent System, due to its robustness for learning in uncertain and unknown environments. This paper proposes a multiagent Reinforcement Learning approach, that uses coordinated actions, which we call strategies and a fusing process to guide the agents. To evaluate the proposed approach, we conduct experiments in the Predator-Prey domain and compare it with other learning techniques. The results demonstrate the efficiency of the proposed approach.