Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality

NIPS 2020, 2020.

Cited by: 0|Views12
EI
Weibo:
Let us forget about CRush Optimism with Pessimism and consider the oracle described in Section 2

Abstract:

We study stochastic structured bandits for minimizing regret. The fact that the popular optimistic algorithms do not achieve the asymptotic instance-dependent regret optimality (asymptotic optimality for short) has recently allured researchers. On the other hand, it is known that one can achieve a bounded regret (i.e., does not grow ind...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments