← Search

Zhezheng Luo

2 accepted papers

2023

Learning Rational Subgoals from Demonstrations and Instructions

AAAI 2023technical

We present a framework for learning useful subgoals that support efficient long-term planning to achieve novel goals. At the core of our framework is a collection of rational subgoals (RSGs), which are essentially binary classifiers over the environmental states. RSGs can be learned from weakly-anno…

Cited by 6SourcePDFScholar
2021

Temporal and Object Quantification Networks

IJCAI 2021poster

We present Temporal and Object Quantification Networks (TOQ-Nets), a new class of neuro-symbolic networks with a structural bias that enables them to learn to recognize complex relational-temporal events. This is done by including reasoning layers that implement finite-domain quantification over obj…

Cited by 7SourcePDFScholar