ROApr 14

Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots

arXiv:2604.1290938.1h-index: 3
AI Analysis

Provides a lightweight continual learning framework for multi-skill humanoid robot control, addressing catastrophic forgetting without complex MoE or large models.

Tree Learning enables humanoid robots to learn multiple locomotion skills sequentially without catastrophic forgetting, achieving higher rewards and 100% skill retention compared to multi-task training in simulation.

As reinforcement learning for humanoid robots evolves from single-task to multi-skill paradigms, efficiently expanding new skills while avoiding catastrophic forgetting has become a key challenge in embodied intelligence. Existing approaches either rely on complex topology adjustments in Mixture-of-Experts (MoE) models or require training extremely large-scale models, making lightweight deployment difficult. To address this, we propose Tree Learning, a multi-skill continual learning framework for humanoid robots. The framework adopts a root-branch hierarchical parameter inheritance mechanism, providing motion priors for branch skills through parameter reuse to fundamentally prevent catastrophic forgetting. A multi-modal feedforward adaptation mechanism combining phase modulation and interpolation is designed to support both periodic and aperiodic motions. A task-level reward shaping strategy is also proposed to accelerate skill convergence. Unity-based simulation experiments show that, in contrast to simultaneous multi-task training, Tree Learning achieves higher rewards across various representative locomotion skills while maintaining a 100% skill retention rate, enabling seamless multi-skill switching and real-time interactive control. We further validate the performance and generalization capability of Tree Learning on two distinct Unity-simulated tasks: a Super Mario-inspired interactive scenario and autonomous navigation in a classical Chinese garden environment.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes