Symbolic metaprogram search improves learning efficiency and explains rule learning in humans
Nature Communications, 2024. [All Versions]. Symbolic models based on program learning successfully explain rule-learning in many domains, but performance degrades quickly as program complexity increases. It remains unclear how to scale symbolic rule-learning methods to model…
- from
- AGI & CoCoSci
- added
- 2026-10-10
- likes
- 0
similar
-
Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning arxiv.org
ICML'20, 2020. [All Versions].
-
Detect, Understand, Act: A Neuro-symbolic Hierarchical Reinforcement Learning Framework link.springer.com
Machine Learning, 2022. [All Versions]. A neuro-symbolic framework that integrates meta-policy learning in inductive logic programming.
-
Meta-Interpretive Learning as Metarule Specialisation arxiv.org
Machine Learning, 2021. [All Versions].
-
Learning Compositional Rules via Neural Program Synthesis proceedings.neurips.cc
NeurIPS'20, 2020. [All Versions].
-
Meta-Interpretive Learning from noisy images link.springer.com
Machine Learning, 2018. [All Versions].
-
The successor representation in human reinforcement learning gershmanlab.com
Nature Human Behavior, 2017. [All Versions].
AGI & CoCoSci › Papers > Domain Specific Language > Cognitive Foundations: “Nature Communications, 2024. [All Versions]. Symbolic models based on program learning successfully explain rule-learning in many domains, but performance degrades quickly as program complexity increases. It remains unclear how to scale symbolic rule-learning methods to model…”