Constrained Meta Agnostic Reinforcement Learning

Karam Daaboul, Florian Kuhm, Tim Joseph, J. Marius Zoellner

Keywords: Meta Learning, Safe Reinforcement Learning

TL;DR: While traditional meta-reinforcement learning algorithms focus on learning how to learn efficiently, our method C-MAML extends this concept by learning how to learn safely by integrating safety constraints into the learning process.

Abstract: Meta-Reinforcement Learning (Meta-RL) aims to acquire meta-knowledge for quick adaptation to diverse tasks. However, applying these policies in real-world environments presents a significant challenge in balancing rapid adaptability with adherence to environmental constraints. Our novel approach, Constraint Model Agnostic Meta Learning (C-MAML), merges meta learning with constrained optimization to address this challenge. C-MAML enables rapid and efficient task adaptation by incorporating task-specific constraints directly into its meta-algorithm framework during the training phase. This fusion results in safer initial parameters for learning new tasks. We demonstrate the effectiveness of C-MAML in simulated locomotion with wheeled robot tasks of varying complexity, highlighting its practicality and robustness in dynamic environments.

Submission Number: 22