Timezone: »

Fitted Q-iteration in continuous action-space MDPs
Remi Munos · András Antos · Csaba Szepesvari

Tue Dec 04 10:30 AM -- 10:40 AM (PST) @ None #None

We consider continuous state, continuous action batch reinforcement learning where the goal is to learn a good policy from a sufficiently rich trajectory generated by another policy. We study a variant of fitted Q-iteration, where the greedy action selection is replaced by searching for a policy in a restricted set of candidate policies by maximizing the average action values. We provide a rigorous theoretical analysis of this algorithm, proving what we believe is the first finite-time bounds for value-function based algorithms for continuous state- and action-space problems.

Author Information

Remi Munos (Google DeepMind)
András Antos (MTA SZTAKI Institute for Computer Science and Control)
Csaba Szepesvari (DeepMind / University of Alberta)

More from the Same Authors