Why deterministic logic is hard to learn but Statistical Relational Learning works

2010/01/01 by Marc Toussaint, Toussaint, Marc
Computer Science · #Machine Learning and Algorithms #Formal Methods in Verification #Computability, Logic, AI Algorithms

paper · doi:10.4230/dagsemproc.10302.6

Abstract

A brief note on why we think that the statistical relational learning framework is a great advancement over deterministic logic – in particular in the context of model-based Reinforcement Learning.

Related

• Induction of Interpretable Possibilistic Logic Theories from Relational\n Data
• Statistical relational learning and neuro-symbolic AI: what does first-order logic offer?
• Learning Rules from Rewards
• A mathematical theory of balancing relational generalization and memorization
• Learning Relational Representations with Auto-encoding Logic Programs