How to Choose a Reinforcement-Learning Algorithm
MCML Authors
Vladimir Golkov
Dr.
* Former Member
Daniel Cremers
Prof. Dr.
Director
Abstract
Vladimir Golkov
Dr.
* Former Member
Daniel Cremers
Prof. Dr.
Director
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.
misc BGM+24
Preprint
Jul. 2024Authors
F. Bongratz • V. Golkov • L. Mautner • L. Della Libera • F. Heetmeyer • F. Czaja • J. Rodemann • D. CremersLinks
arXiv GitHubResearch Areas
BibTeXKey: BGM+24