cff-version: 1.2.0 abstract: "<p>This Dataset contains the code associated with the research paper "What model does MuZero learn?" published at ECAI 2024.</p><p>Our research aims to study to what extent models learned by MuZero support policy improvement.</p><p>The code here contains scripts to evaluate models learned by MuZero.</p><p>Two files implement our policy evaluation and improvement experiments with common functionalities implemented in base.py.</p><p>The other scripts are for scaling experiments by automatically generating and launching experiment configurations.</p><p>To train MuZero agents, we used https://github.com/YeWR/EfficientZero and https://github.com/werner-duvaud/muzero-general.</p>" authors: - family-names: He given-names: Jinke orcid: "https://orcid.org/0000-0002-8528-8650" - family-names: Moerland given-names: Thomas orcid: "https://orcid.org/0000-0002-3367-1367" - family-names: de Vries given-names: Joery - family-names: Oliehoek given-names: Frans orcid: "https://orcid.org/0000-0003-4372-5055" title: "Code associated with the publication: What model does MuZero learn?" keywords: version: 1 identifiers: - type: doi value: 10.4121/a88194f4-45a5-41ae-9cda-0116b78473e5.v1 license: MIT date-released: 2024-12-11