Switching between different state representations in reinforcement learning

This paper proposes a reinforcement learning architecture con taining multiple "experts", each of which is a specialist in a dif ferent region in the overall state space. The central idea is that the different experts use qualitatively different (but sufficiently Markov) state representations, each of which captures different information regarding the true underlying world state, and which for that reason is suitable for a different part of the state space. The experts themselves learn to switch to another state represen tation (other expert) by having switching actions. Value functions can be learned using standard reinforcement learning algorithms. This architecture has important advantages in RL problems that have large state spaces or where a sensor system must inherently choose between mutually exclusive state representations. Experi ments in a small, proof-of-principle experiment as well as a larger, more realistic experiment illustrate the validity of this approach.