Proceedings of the 18th European Conference on Artificial Intelligence pages:779-780
ECAI edition:18 location:Patras, Greece date:21-25 July 2008
A common solution approach to reinforcement learning problems with large state spaces (where value functions cannot be represented exactly) is to compute an approximation of the value function in terms of state features. However, little attention has been paid to the cost of computing these state features (e.g., search-based features). To this end, we introduce a cost-sensitive sparse linear-value function approximation algorithm --- FOVEA --- and demonstrate its performance on an experimental domain with a range of feature costs.