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.
Related
Publications :
Luis
Nunes and Eugenio Oliveira in Proceedings of the
Second Symposium on Adaptive Agents and Multi-Agent Systems,
Imperial College, London, April 2002