Please use this identifier to cite or link to this item:
|Title:||On learning by exchanging advice|
|Abstract:||One of the main questions concerning learning in Multi-Agent Systems is: ”(How) can agents benefit from mutual interaction during the learning process?”. This paper describes the study of an interactive advice-exchange mechanism as a possible way to improve agents’ learning performance. The advice-exchange technique, discussed here, uses supervised learning (backpropagation), where reinforcement is not directly coming from the environment but is based on advice given by peers with better performance score (higher confidence), 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: RandomWalk (hill-climbing), Simulated Annealing, Evolutionary Algorithms and Q-Learning. The problem used for evaluation is a simplified traffic-control simulation. In the following text the reader can find a description of the traffic simulation and Learning Agents (focused on the advice-exchange mechanism), a discussion of the first results obtained and suggested techniques to overcome the problems that have been observed. Initial results indicate that advice-exchange can improve learning speed, although ”bad advice” and/or blind reliance can disturb the learning performance. The use of supervised learning to incorporate advice given from non-expert peers using different learning algorithms, in problems where no supervision information is available, is, to the best of the authors’ knowledge, a new concept in the area of Multi-Agent Systems Learning.|
|Appears in Collections:||CTI-RI - Artigos em revistas científicas internacionais com arbitragem científica|
Files in This Item:
|On Learning By Exchanging Advice.pdf||279.33 kB||Adobe PDF||View/Open|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.