English

How to Choose a Reinforcement-Learning Algorithm

Machine Learning 2024-07-31 v1 Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning

Abstract

The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://rl-picker.github.io/.

Keywords

Cite

@article{arxiv.2407.20917,
  title  = {How to Choose a Reinforcement-Learning Algorithm},
  author = {Fabian Bongratz and Vladimir Golkov and Lukas Mautner and Luca Della Libera and Frederik Heetmeyer and Felix Czaja and Julian Rodemann and Daniel Cremers},
  journal= {arXiv preprint arXiv:2407.20917},
  year   = {2024}
}

Comments

40 pages

R2 v1 2026-06-28T17:58:19.007Z