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/.
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