On Measuring the Impact of Human Actions in the Machine Learning of a Board Game's Playing Policies

11/30/2006
by   Dimitris Kalles, et al.
0

We investigate systematically the impact of human intervention in the training of computer players in a strategy board game. In that game, computer players utilise reinforcement learning with neural networks for evolving their playing strategies and demonstrate a slow learning speed. Human intervention can significantly enhance learning performance, but carry-ing it out systematically seems to be more of a problem of an integrated game development environment as opposed to automatic evolutionary learning.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset