Problem
Research questions and friction points this paper is trying to address.
partial observability
action model learning
neurosymbolic approaches
Neurosymbolic Action Model Learning under Partial Observability
🤖 AI Summary
本文提出NeSyAM，一种新的神经符号建模方法，用于在部分可观测条件下学习动作模型，解决现有方法无法处理信息不全的问题。
📝 Abstract
AI planning studies how an agent can reach a goal by executing a sequence of actions. To plan correctly, the agent needs an action model describing when each action can be executed and how it changes the world. Constructing such models by hand requires domain expertise, and can be costly and error-prone. Action models can instead be learned from available data using existing neurosymbolic approaches, but they currently assume access to complete traces of fully observable images . These approaches fail to learn action models under partial observability where some of the images might not be present or are not fully informative of the current state of the world. Hence, this paper proposes NeSyAM, a novel neurosymbolic modeling paradigm for action model learning under partial observability. In addition, the paper presents a unified variational framework for theoretically analysing the limitations of existing methods compared to our proposed approach. NeSyAM is then tested extensively on six visual planning domains and three observation regimes to show it consistently recovers relevant parts of the true action model under partial observability.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Neurosymbolic Modeling
Partial Observability
Action Model Learning
Variational Framework
🔎 Similar Papers
No similar papers found.
