MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
Zohar Rimon, Tom Jurgenson, Orr Krupnik, Gilad Adler, Aviv Tamar
Abstract
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.
BibTeX
@inproceedings{
rimon2024mamba,
title={{MAMBA}: an Effective World Model Approach for Meta-Reinforcement Learning},
author={Zohar Rimon and Tom Jurgenson and Orr Krupnik and Gilad Adler and Aviv Tamar},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=1RE0H6mU7M}
}