Constrained Meta Agnostic Reinforcement Learning

2024/06/20 by Karam Daaboul, Daaboul, Karam, Florian Kuhm +5
Engineering · #FOS: Computer and information sciences #Fault Detection and Control Systems #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2406.14047

openalex publication_date 2024/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Directed-MAML: Meta Reinforcement Learning Algorithm with Task-directed Approximation
• Robotic Control Using Model Based Meta Adaption
• Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors
• Curriculum in Gradient-Based Meta-Reinforcement Learning
• Constrained Meta-Reinforcement Learning for Adaptable Safety Guarantee with Differentiable Convex Programming