MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
This addresses the challenge of inefficient exploration in meta-RL for developing more generalizing agents, though it is incremental as it builds on existing methods.
The paper tackles the problem of low sample efficiency in meta-reinforcement learning by proposing a model-based approach, achieving up to 15x better sample efficiency and greater return on benchmark domains.
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.