Abstract
Our goal is to build embodied agents that can learn inductively generalizable spatial concepts in a continual manner, e.g, constructing a tower of a given height. Existing work suffers from certain limitations (a) (Liang et al., 2023) and their multi-modal extensions, rely heavily on prior knowledge and are not grounded in the demonstrations (b) (Liu et al., 2023) lack the ability to generalize due to their purely neural approach. A key challenge is to achieve a fine balance between symbolic representations which have the capability to generalize, and neural representations that are physically grounded. In response, we propose a neuro-symbolic approach by expressing inductive concepts as symbolic compositions over grounded neural concepts. Our key insight is to decompose the concept learning problem into the following steps 1) Sketch: Getting a programmatic representation for the given instruction 2) Plan: Perform Model-Based RL over the sequence of grounded neural action concepts to learn a grounded plan 3) Generalize: Abstract out a generic (lifted) Python program to facilitate generalizability. Continual learning is achieved by interspersing learning of grounded neural concepts with higher level symbolic constructs. Our experiments demonstrate that our approach significantly outperforms existing baselines in terms of its ability to learn novel concepts and generalize inductively.
Abstract (translated)
我们的目标是构建能够以连续的方式学习归纳通用空间概念的 embodied 代理，例如，构建一个指定高度的塔。现有工作存在某些局限性：（a）(Liang 等人，2023) 和他们的多模态扩展，严重依赖先验知识，并且缺乏演示（b）(Liu 等人，2023) 的物理基础，无法进行泛化。一个关键挑战是实现符号表示与具有泛化能力的神经表示之间的良好平衡。为了应对这一挑战，我们提出了一个基于神经符号的方法，通过将归纳性概念表达为 grounded 神经概念的符号组合来表示。我们的关键见解是将概念学习问题分解为以下步骤：1) 草图：为给定指令获得程序化表示；2）规划：在 grounded 神经动作概念的序列上执行基于模型的强化学习，以学习一个 grounded 计划；3）泛化：抽象出通用的（lifted）Python 程序，以促进泛化。持续学习是通过在 grounded 神经概念的学习中插入更高层次的符号构建来实现的。我们的实验证明，与其他现有基线相比，我们的方法在学习和泛化方面的表现显著出色。
URL
https://arxiv.org/abs/2404.07774
