Universal Morphology Control via Contextual Modulation
This addresses the challenge of multi-task reinforcement learning for robotics, enabling more efficient and adaptable control across diverse robot designs, though it is incremental in building on existing graph and transformer methods.
The paper tackled the problem of learning a universal control policy across different robot morphologies by proposing a hierarchical architecture with contextual modulation, resulting in improved learning performance and better zero-shot generalization to unseen morphologies.
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.