Prototype- or curriculum-based task inference for continual embodied learning

Develop efficient prototype representations from prior data distributions or curricula to perform task inference when learning new tasks in embodied agents, enabling accurate identification of task structure and faster adaptation in continual learning settings.

Background

Continual learning in robotics requires mechanisms to recognize and adapt to new tasks without forgetting prior capabilities. The authors identify the need for efficient prototype or curriculum constructs derived from prior distributions to infer tasks when encountering novel situations.

This open problem seeks principled formulations and algorithms that leverage prototypes or curricula to guide task inference, thereby enhancing generalization and reducing the sample complexity of learning new embodied behaviors.

References

Open research problems and viable approaches include: 1) mixing different proportions of prior data distribution when fine-tuning on the latest data to alleviate catastrophic forgetting , 2) developing efficient prototypes from prior distributions or curricula for task inference in learning new tasks, 3) improving training stability and sample efficiency of online learning algorithms, 4) identifying principled ways to seamlessly incorporate large-capacity models into control frameworks, potentially through hierarchical learning or slow-fast control, for real-time inference.

— Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI  (2407.06886 - Liu et al., 2024) in Section 8, Challenges and Future Directions – Continual Learning