English

Learning with Value-Ramp

Machine Learning 2017-04-25 v2

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-22T15:18:06.653Z