Enregistré dans:
Détails bibliographiques
Auteurs principaux: Rimon, Zohar, Jurgenson, Tom, Krupnik, Orr, Adler, Gilad, Tamar, Aviv
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.09859
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909137766449152
author Rimon, Zohar
Jurgenson, Tom
Krupnik, Orr
Adler, Gilad
Tamar, Aviv
author_facet Rimon, Zohar
Jurgenson, Tom
Krupnik, Orr
Adler, Gilad
Tamar, Aviv
contents Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional task distributions. In parallel, model-based RL methods have been successful in solving partially observable MDPs, of which meta-RL is a special case. In this work, we leverage this success and propose a new model-based approach to meta-RL, based on elements from existing state-of-the-art model-based and meta-RL methods. We demonstrate the effectiveness of our approach on common meta-RL benchmark domains, attaining greater return with better sample efficiency (up to $15\times$) while requiring very little hyperparameter tuning. In addition, we validate our approach on a slate of more challenging, higher-dimensional domains, taking a step towards real-world generalizing agents.
format Preprint
id arxiv_https___arxiv_org_abs_2403_09859
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
Rimon, Zohar
Jurgenson, Tom
Krupnik, Orr
Adler, Gilad
Tamar, Aviv
Machine Learning
Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional task distributions. In parallel, model-based RL methods have been successful in solving partially observable MDPs, of which meta-RL is a special case. In this work, we leverage this success and propose a new model-based approach to meta-RL, based on elements from existing state-of-the-art model-based and meta-RL methods. We demonstrate the effectiveness of our approach on common meta-RL benchmark domains, attaining greater return with better sample efficiency (up to $15\times$) while requiring very little hyperparameter tuning. In addition, we validate our approach on a slate of more challenging, higher-dimensional domains, taking a step towards real-world generalizing agents.
title MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2403.09859