In Reinforcement Learning (RL), it is common to use optimistic initialization of value functions to encourage exploration. However, such an approach generally depends on the domain, viz., the scale of the rewards must be known, and the feature representation must have a constant norm. We present a simple approach that performs optimistic initialization with less dependence on the domain.
@article{arxiv.1410.4604,
title = {Domain-Independent Optimistic Initialization for Reinforcement Learning},
author = {Marlos C. Machado and Sriram Srinivasan and Michael Bowling},
journal= {arXiv preprint arXiv:1410.4604},
year = {2014}
}