Learning in Multi-Agent Systems

This is a reasearh line  being developed at NIAD&R - Distributed Artificial Intelligence and Robotics Group (LIACC). The researchers involved in the project are:
 

    Learning by Advice exchanging


This research line is mainly covered by Ph.D. work of Luis Nunes under supervision of Prof. Eugénio Oliveira

One of the main questions concerning learning in Multi-Agent Systems is: “(How) can agents benefit from mutual interaction during the learning process?”
We aim at developing an interactive advice-exchange mechanism as a possible way to improve agents’ learning performance.
heterogeneous Agents, embedding different learning capabilities and algorithms work together to enhance the performance of a heterogeneous group of Learning Agents (LAs).
The LAs are facing similar problems, in an environment where only reinforcement information is available. Each LA applies a different, well known, learning technique: Random Walk (ako hill-climbing), Simulated Annealing, Evolutionary Algorithms and Q-Learning.
The problem used for evaluation is a simplified traffic-control simulation.