Action Selection methods using Reinforcement Learning

Abstract

Action Selection schemes, when translated into precise algorithms, typically involve considerable design effort and tuning of parameters. Little work has been done on solving the problem using learning. This paper compares eight different methods of solving the action selection problem using Reinforcement Learning (learning from rewards). The methods range from centralised and cooperative to decentralised and selfish. They are tested in an artificial world and their performance, memory requirements and reactiveness are compared. Finally, the possibility of more exotic, ecosystem-like decentralised models are considered.