Skip to main content
WorldCist'20 - 8th World Conference on Information Systems and Technologies

Full Program »

Overcoming Reinforcement Learning limits with Inductive Logic Programming

This work presents some approaches to overcome current Reinforcement Learning limits. We implement a simple virtual environment and some state-of-the-art Reinforcement Learning algorithms for testing and producing a baseline for comparison. Then we implement a Relational Reinforcement Learning algorithm that shows superior performance to the baseline but requires introducing human knowledge. We also propose that model-based Reinforcement Learning can help us overcome some of the barriers. For better World models, we explore Inductive Logic Programming methods, such as First-Order Inductive Learner, and develop an improved version of it, more adequate to Reinforcement Learning environments. Finally we develop a novel Neural Network architecture, the Inductive Logical Neural Network, to fill the gaps of the previous implementations, that shows great promise.

Filipe Marinho da Rocha
Faculdade de Ciências da Universidade do Porto
Portugal

Luís Paulo Reis
Faculdade de Engenharia da Universidade do Porto
Portugal

Vítor Santos Costa
Faculdade de Ciências da Universidade do Porto
Portugal

 


Powered by OpenConf®
Copyright ©2002-2018 Zakon Group LLC