A Multiple Representation Approach to Learning Dynamical Systems

We examine the problem of learning a model of a deterministic dynamical systems from experience. A handful of representation schemes have been proposed for capturing such systems, including POMDPs, PSRs, EPSRs, Diversity, and PSTs. We argue that no single representation should be expected to be ideal in all situations and describe an approach for learning the most succinct representation of an unknown dynamical system.