Publikation
Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning
Leonhard Keller; Daniel Tanneberg; Jan Peters
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2503.21406, Pages 1-8, arXiv, 2025.
Zusammenfassung
mitation learning is a popular method for teach-
ing robots new behaviors. However, most existing methods
focus on teaching short, isolated skills rather than long, multi-
step tasks. To bridge this gap, imitation learning algorithms
must not only learn individual skills but also an abstract
understanding of how to sequence these skills to perform
extended tasks effectively. This paper addresses this challenge
by proposing a neuro-symbolic imitation learning framework.
Using task demonstrations, the system first learns a symbolic
representation that abstracts the low-level state-action space.
The learned representation decomposes a task into easier
subtasks and allows the system to leverage symbolic planning
to generate abstract plans. Subsequently, the system utilizes
this task decomposition to learn a set of neural skills capable
of refining abstract plans into actionable robot commands.
Experimental results in three simulated robotic environments
demonstrate that, compared to baselines, our neuro-symbolic
approach increases data efficiency, improves generalization
capabilities, and facilitates interpretability.