Timezone: »

The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity
Mark Sellke · Aleksandrs Slivkins
Event URL: https://openreview.net/forum?id=vVwoKE4MMAP »

We consider \emph{incentivized exploration}: a version of multi-armed bandits where the choice of arms is controlled by self-interested agents, and the algorithm can only issue recommendations. The algorithm controls the flow of information, and the information asymmetry can incentivize the agents to explore. Prior work achieves optimal regret rates up to multiplicative factors that become arbitrarily large depending on the Bayesian priors, and scale exponentially in the number of arms. A more basic problem of sampling each arm once runs into similar factors.We focus on the \emph{price of incentives}: the loss in performance, broadly construed, incurred for the sake of incentive-compatibility. We prove that Thompson Sampling, a standard bandit algorithm, is incentive-compatible if initialized with sufficiently many data points. The performance loss due to incentives is therefore limited to the initial rounds when these data points are collected.The problem is largely reduced to that of sample complexity: how many rounds are needed? We address this question, providing matching upper and lower bounds and instantiating them in various corollaries. Typically, the optimal sample complexity is polynomial in the number of arms and exponential in the ``strength of beliefs".

Author Information

Mark Sellke (Stanford University)
Aleksandrs Slivkins (Microsoft Research NYC)

More from the Same Authors