VQ-CNMP: Neuro-Symbolic Skill Learning for Bi-Level Planning
This addresses skill learning for robotics or AI systems, but appears incremental as it builds on existing neuro-symbolic and planning methods.
The paper tackles the problem of discovering high-level skill representations from unlabeled demonstration data and proposes a bi-level planning pipeline using gradient-based planning. The result includes testing skill discovery under various conditions, using Multi-Modal LLMs to label learned skills, and evaluating high-level and low-level planning performance.
This paper proposes a novel neural network model capable of discovering high-level skill representations from unlabeled demonstration data. We also propose a bi-level planning pipeline that utilizes our model using a gradient-based planning approach. While extracting high-level representations, our model also preserves the low-level information, which can be used for low-level action planning. In the experiments, we tested the skill discovery performance of our model under different conditions, tested whether Multi-Modal LLMs can be utilized to label the learned high-level skill representations, and finally tested the high-level and low-level planning performance of our pipeline.