制約付きメタ強化学習
Constrained Meta Agnostic Reinforcement Learning
メタ強化学習に制約最適化を組み込み、タスク固有の制約を訓練時に考慮することで、新しいタスクへの迅速な適応と安全性を両立させるC-MAMLを提案し、車輪ロボットの移動タスクで有効性を示した。
著者: Karam Daaboul, Florian Kuhm, Tim Joseph, J. Marius Zoellner
分類: cs.LG
原文アブストラクト
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.
