(Almost) Free Incentivized Exploration from Decentralized Learning Agents

10/27/2021
by   Chengshuai Shi, et al.
5

Incentivized exploration in multi-armed bandits (MAB) has witnessed increasing interests and many progresses in recent years, where a principal offers bonuses to agents to do explorations on her behalf. However, almost all existing studies are confined to temporary myopic agents. In this work, we break this barrier and study incentivized exploration with multiple and long-term strategic agents, who have more complicated behaviors that often appear in real-world applications. An important observation of this work is that strategic agents' intrinsic needs of learning benefit (instead of harming) the principal's explorations by providing "free pulls". Moreover, it turns out that increasing the population of agents significantly lowers the principal's burden of incentivizing. The key and somewhat surprising insight revealed from our results is that when there are sufficiently many learning agents involved, the exploration process of the principal can be (almost) free. Our main results are built upon three novel components which may be of independent interest: (1) a simple yet provably effective incentive-provision strategy; (2) a carefully crafted best arm identification algorithm for rewards aggregated under unequal confidences; (3) a high-probability finite-time lower bound of UCB algorithms. Experimental results are provided to complement the theoretical analysis.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/02/2021

Pure Exploration in Multi-armed Bandits with Graph Side Information

We study pure exploration in multi-armed bandits with graph side-informa...
research
10/27/2021

Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization

Despite the significant interests and many progresses in decentralized m...
research
10/20/2018

Quantifying the Burden of Exploration and the Unfairness of Free Riding

We consider the multi-armed bandit setting with a twist. Rather than hav...
research
02/15/2023

Bandit Social Learning: Exploration under Myopic Behavior

We study social learning dynamics where the agents collectively follow a...
research
11/19/2018

Decentralized Exploration in Multi-Armed Bandits

We consider the decentralized exploration problem: a set of players coll...
research
03/01/2021

Information Discrepancy in Strategic Learning

We study the effects of information discrepancy across sub-populations o...
research
06/30/2020

Forced-exploration free Strategies for Unimodal Bandits

We consider a multi-armed bandit problem specified by a set of Gaussian ...

Please sign up or login with your details

Forgot password? Click here to reset