Adaptive Simulation-based Training of AI Decision-makers using Bayesian Optimization

Abstract

This work studies how an AI-controlled dog-fighting agent with tunable decisionmaking parameters can learn to optimize performance against an intelligent adversary, as measured by a stochastic objective function evaluated on simulated combat engagements. Gaussian process Bayesian optimization (GPBO) techniques are developed to automatically learn global… (More)

Topics

Cite this paper

@article{Israelsen2017AdaptiveST, title={Adaptive Simulation-based Training of AI Decision-makers using Bayesian Optimization}, author={Brett W. Israelsen and Nisar R. Ahmed and Kenneth Center and Roderick Green and Winston Bennett}, journal={CoRR}, year={2017}, volume={abs/1703.09310} }