We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications...
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
In this paper we present an approach for reducing the memory footprint requirement of temporal difference methods in which the set of states is finite. We use case-based generaliza...