02/02/2021

Lenient Regret for Multi-Armed Bandits

Nadav Merlis, Shie Mannor

Keywords:

Abstract Paper Similar Papers

Abstract: We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. For example, in large problems, or when the interaction with the environment is brief, finding an optimal arm is infeasible, and regret-minimizing algorithms tend to over-explore. To overcome this issue, algorithms for such settings should instead focus on playing near-optimal arms. To this end, we suggest a new, more lenient, regret criterion that ignores suboptimality gaps smaller than some ε. We then present a variant of the Thompson Sampling (TS) algorithm, called ε-TS, and prove its asymptotic optimality in terms of the lenient regret. Importantly, we show that when the mean of the optimal arm is high enough, the lenient regret of ε-TS is bounded by a constant. Finally, we show that ε-TS can be applied to improve the performance when the agent knows a lower bound of the suboptimality gaps.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38949121
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 13:06 
 0
 0
 0
 0
 12:07 
 0
 0
 0
 0
 13:22 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 15:29 
 0
 0
 0
 0
 18:13 
 0
 0
 0
 0
 14:18 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 14:35 
 0
 0
 0
 0
 2:49 
 0
 0
 0
 0
 3:14 
 0
 0
 0
 0
 14:00 
 0
 0
 0
 0
 3:09 
 0
 0
 0
 0
 15:20 
 0
 0
 0
 0
 15:22 
 0
 0
 0
 0
 10:40 
 0
 0
 0
 0
 17:11 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 14:29 
 0
 0
 0
 0
 2:52 
 0
 0
 0
 0
 3:01 
 0
 0
 0
 0
 15:30 
 0
 0
 0
 0
 4:17 
 0
 0
 0
 0
 3:26 
 0
 0
 0
 0
 17:20 
 0
 0
 0
 0
 14:58 
 0
 0
 0
 0
 2:37 
 0
 0
 0
 0
 19:29 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 20:29 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 10:23 
 0
 0
 0
 0
 3:06 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 17:56 
 0
 0
 0
 0
 14:17 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 2:51 
 0
 0
 0
 0
 17:35