Learning Options for Compositional Motor Control with Adapter Banks
cs.LG, cs.RO, q-bio.NC
Submitted: 2026-09-15
Updated: 2026-09-15
License: http://creativecommons.org/licenses/by/4.0/
The gist: Learning flexible motor primitives is a hallmark of skilled motor control.
Terminology
Abstract
Learning flexible motor primitives is a hallmark of skilled motor control. Recent neuroscience theory proposes that motor primitives may be implemented as low-rank perturbations of a shared recurrent network, but leaves open how such a system is learned. We translate this principle into a novel architecture for learning motor skills end-to-end: a shared recurrent core modulated by a bank of residual adapters, each selected by a discrete latent code. Trained on closed-loop biomechanical control, the adapters develop emergent low-rank perturbations of the recurrent dynamics despite no architectural rank constraint, placing task representations in disparate subspaces of the shared core network. A simple high-level policy over the learned options, optimized while the whole network is frozen, sequences the low-rank adapters to produce novel out-of-distribution movements. We demonstrate the ability to generalize to novel motor sequences within the closed-loop control setting, improving on the generalization error of a task-input-conditioned multitask baseline by upto order of magnitude.
Sources
- Diversity is All You Need: Learning Skills without a Reward Function
- Separating the what and how of compositional computation to enable reuse and continual learning
- LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
- MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts
- Compositional meta-learning through probabilistic task inference
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks