Towards Learned Anticipation in Complex Stochastic Environments
Abstract
We describe a novel methodology by which a software agent can learn to predict future events in complex stochastic environmentals. It is particularly relevant to environments that are construed specifically so as to be able to support high-performance software agents, such as video games. We present results gathered from a first prototype of our approach. The technique presented may have applications that range beyond improving agent performance, in particular to user modeling in the service of automated game testing.