Overcoming Reinforcement Learning Limits with Inductive Logic Programming

• Type: Article in International Conference Proceedings Book
• Date: 2020

Authors

Filipe Marinho Rocha (Author) Other; Luís Paulo Reis (Author) FEUP

Conference proceedings International

Title: WorldCIST (2)

Pages: 414-423

8th World Conference on Information Systems and Technologies, WorldCIST 2020

7 April 2020 through 10 April 2020

Indexing

Scopus - 0 Citations

Other information

Authenticus ID: P-00S-APT

DOI: 10.1007/978-3-030-45691-7_38

Abstract (EN): 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 Logic Neural Network, to fill the gaps of the previous implementations, that shows great promise. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 10