Selecting the state-representation in reinforcement learning
Odalric Maillard, Rémi Munos and Daniil Ryabko
The problem of selecting the right state-representation in a reinforcement learning problem is considered. Several models (functions mapping past observations to a ﬁnite set) of the observations are given, and it is known that for at least one of these models the resulting state dynamics are indeed Markovian. Without know ing neither which of the models is the correct one, nor what are the probabilistic characteristics of the resulting MDP, it is required to obtain as much reward as the optimal policy for the correct model (or for the best of the correct models, if there are several). We propose an algorithm that achieves that, with a regret of order T2/3 where T is the horizon time.
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Rémi Munos|
|Deposited On:||21 February 2012|