We study a learning principle based on the intuition of forming ramps. The agent tries to follow an increasing sequence of values until the agent meets a peak of reward. The resulting Value-Ramp algorithm is natural, easy to configure, and has a robust implementation with natural numbers.
@article{arxiv.1608.03647,
title = {Learning with Value-Ramp},
author = {Tom J. Ameloot and Jan Van den Bussche},
journal= {arXiv preprint arXiv:1608.03647},
year = {2017}
}
Comments
Version 2: fixed notation in definition of transition + clarified a sentence in the Introduction