PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Neuroevolutionary reinforcement learning for generalized helicopter control
R. Koppejan and S. Whiteson
In: GECCO 2009, 12-14 June, Shanghai, China.

Abstract

Helicopter hovering is an important challenge problem in the field of reinforcement learning. This paper considers several neuroevolutionary approaches to discovering robust controllers for a generalized version of the problem used in the 2008 Reinforcement Learning Competition, in which wind in the helicopter's environment varies from run to run. We present the simple model-free strategy that won first place in the competition and also describe several more complex model-based approaches. Our empirical results demonstrate that neuroevolution is effective at optimizing the weights of multi-layer perceptrons, that linear regression is faster and more effective than evolution for learning models, and that model-based approaches can outperform the simple model-free strategy, especially if prior knowledge is used to aid model learning.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:6726
Deposited By:Christof Monz
Deposited On:08 March 2010