GACL: Grounded Adaptive Curriculum Learning with Active Task and Performance Monitoring
This addresses the challenge of reducing engineering effort and improving performance in robotics training, though it is incremental as it builds on existing automated curriculum learning approaches.
The paper tackled the problem of automating curriculum learning for complex robotics tasks, which typically require manual design, by proposing a framework that achieved 6.8% and 6.1% higher success rates in navigation and locomotion tasks compared to state-of-the-art methods.
Curriculum learning has emerged as a promising approach for training complex robotics tasks, yet current applications predominantly rely on manually designed curricula, which demand significant engineering effort and can suffer from subjective and suboptimal human design choices. While automated curriculum learning has shown success in simple domains like grid worlds and games where task distributions can be easily specified, robotics tasks present unique challenges: they require handling complex task spaces while maintaining relevance to target domain distributions that are only partially known through limited samples. To this end, we propose Grounded Adaptive Curriculum Learning, a framework specifically designed for robotics curriculum learning with three key innovations: (1) a task representation that consistently handles complex robot task design, (2) an active performance tracking mechanism that allows adaptive curriculum generation appropriate for the robot's current capabilities, and (3) a grounding approach that maintains target domain relevance through alternating sampling between reference and synthetic tasks. We validate GACL on wheeled navigation in constrained environments and quadruped locomotion in challenging 3D confined spaces, achieving 6.8% and 6.1% higher success rates, respectively, than state-of-the-art methods in each domain.