Optimistic Agents are Asymptotically Optimal

Sunehag, Peter, Hutter, Marcus

arXiv.org Artificial Intelligence 

We use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic case we provide finite error bounds.

Duplicate Docs Excel Report

None found

Similar Docs  Excel Report  more

None found