文脈変調による汎用形態制御
Universal Morphology Control via Contextual Modulation
ロボットの形態に依存した制御パラメータをハイパーネットワークで生成し、固定注意機構で四肢間の相互作用を調整する階層的アーキテクチャを提案。多様な形態での学習性能と未見形態へのゼロショット汎化を向上させた。
著者: Zheng Xiong, Jacob Beck, Shimon Whiteson
分類: cs.AI, cs.RO, stat.ML
原文アブストラクト
Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. However, it poses a challenging multi-task reinforcement learning problem, as the optimal policy may be quite different across robots and critically depend on the morphology. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies, but pay little attention to the dependency of a robot's control policy on its morphology context. In this paper, we propose a hierarchical architecture to better model this dependency via contextual modulation, which includes two key submodules: (1) Instead of enforcing hard parameter sharing across robots, we use hypernetworks to generate morphology-dependent control parameters; (2) We propose a fixed attention mechanism that solely depends on the morphology to modulate the interactions between different limbs in a robot. Experimental results show that our method not only improves learning performance on a diverse set of training robots, but also generalizes better to unseen morphologies in a zero-shot fashion.
