Timezone: »

Provably adaptive reinforcement learning in metric spaces
Tongyi Cao · Akshay Krishnamurthy

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #506

We study reinforcement learning in continuous state and action spaces endowed with a metric. We provide a refined analysis of the algorithm of Sinclair, Banerjee, and Yu (2019) and show that its regret scales with the zooming dimension of the instance. This parameter, which originates in the bandit literature, captures the size of the subsets of near optimal actions and is always smaller than the covering dimension used in previous analyses. As such, our results are the first provably adaptive guarantees for reinforcement learning in metric spaces.

Author Information

Tongyi Cao (University of Massachusetts Amherst)
Akshay Krishnamurthy (Microsoft)

More from the Same Authors