Dissemin is shutting down on January 1st, 2025

Links

Tools

Export citation

Search in Google Scholar

Heuristic Selection of Actions in Multiagent Reinforcement Learning.

Proceedings article published in 2007 by Reinaldo A. C. Bianchi ORCID, Carlos H. C. Ribeiro, Anna Helena Reali Costa
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Question mark in circle
Preprint: policy unknown
Question mark in circle
Postprint: policy unknown
Question mark in circle
Published version: policy unknown

Abstract

This work presents a new algorithm, called Heuris- tically Accelerated Minimax-Q (HAMMQ), that al- lows the use of heuristics to speed up the well- known Multiagent Reinforcement Learning algo- rithm Minimax-Q. A heuristic function H that in- fluences the choice of the actions characterises the HAMMQ algorithm. This function is associated with a preference policy that indicates that a cer- tain action must be taken instead of another. A set of empirical evaluations were conducted for the proposed algorithm in a simplified simulator for the robot soccer domain, and experimental results show that even very simple heuristics enhances sig- nificantly the performance of the multiagent rein- forcement learning algorithm.