Saved in:
Bibliographic Details
Main Author: Mercier, Jean-Marc
Format: Recurso digital
Language:
Published: Zenodo 2025
Online Access:https://doi.org/10.5281/zenodo.15163410
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902081876525056
author Mercier, Jean-Marc
author_facet Mercier, Jean-Marc
contents <pre>We propose a self-contained, detailed, description of a scalable standardized kernel (RKHS) approach to popular reinforcement learning algorithms, where agents interact with environments having continuous states and discrete actions spaces, dealing with possibly unstructured data. These algorithms, namely Q-Learning, Actor Critic, Q-Value Gradient, Hamilton-Jacobi-Bellman (HJB) and Heuristic Controls, are implemented with a RKHS library (\cite{codpy}) using default settings. We show that this approach to reinforcement learning is accurate, robust, sample efficient and versatile, as we benchmark our algorithms in this paper on simple games and use them as a baseline for our applications.</pre>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_15163410
institution Zenodo
language
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle A Scalable Kernel Approach to Reinforcement Learning
Mercier, Jean-Marc
<pre>We propose a self-contained, detailed, description of a scalable standardized kernel (RKHS) approach to popular reinforcement learning algorithms, where agents interact with environments having continuous states and discrete actions spaces, dealing with possibly unstructured data. These algorithms, namely Q-Learning, Actor Critic, Q-Value Gradient, Hamilton-Jacobi-Bellman (HJB) and Heuristic Controls, are implemented with a RKHS library (\cite{codpy}) using default settings. We show that this approach to reinforcement learning is accurate, robust, sample efficient and versatile, as we benchmark our algorithms in this paper on simple games and use them as a baseline for our applications.</pre>
title A Scalable Kernel Approach to Reinforcement Learning
url https://doi.org/10.5281/zenodo.15163410