One-bit feedback is sufficient for upper confidence bound policies
Machine Learning
2020-12-08 v1 Machine Learning
Abstract
We consider a variant of the traditional multi-armed bandit problem in which each arm is only able to provide one-bit feedback during each pull based on its past history of rewards. Our main result is the following: given an upper confidence bound policy which uses full-reward feedback, there exists a coding scheme for generating one-bit feedback, and a corresponding decoding scheme and arm selection policy, such that the ratio of the regret achieved by our policy and the regret of the full-reward feedback policy asymptotically approaches one.
Keywords
Cite
@article{arxiv.2012.02876,
title = {One-bit feedback is sufficient for upper confidence bound policies},
author = {Daniel Vial and Sanjay Shakkottai and R. Srikant},
journal= {arXiv preprint arXiv:2012.02876},
year = {2020}
}