Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 1151-1160, 2019.

Cited by: 29|Views47
EI

Abstract:

This paper establishes that optimistic algorithms attain gap-dependent and non-asymptotic logarithmic regret for episodic MDPs. In contrast to prior work, our bounds do not suffer a dependence on diameter-like quantities or ergodicity, and smoothly interpolate between the gap dependent logarithmic-regret, and the O(root HSAT)-minimax rate...More

Code:

Data:

Your rating :
0

 

Tags
Comments