Authors:
Raz Yerushalmi
1
;
Guy Amir
2
;
Achiya Elyasaf
3
;
David Harel
1
;
Guy Katz
2
and
Assaf Marron
1
Affiliations:
1
Department of Computer Science and Applied Mathematics, Weizmann Institute of Science, Rehovot 76100, Israel
;
2
School of Computer Science and Engineering, The Hebrew University of Jerusalem, Givat Ram, Jerusalem 91904, Israel
;
3
Software and Information Systems Engineering, Ben-Gurion University of the Negev, Beer-Sheva 8410501, Israel
Keyword(s):
Machine Learning, Scenario-based Modeling, Rule-based Specifications, Domain Expertise.
Abstract:
Deep reinforcement learning has proven remarkably useful in training agents from unstructured data. However, the opacity of the produced agents makes it difficult to ensure that they adhere to various requirements posed by human engineers. In this work-in-progress report, we propose a technique for enhancing the reinforcement learning training process (specifically, its reward calculation), in a way that allows human engineers to directly contribute their expert knowledge, making the agent under training more likely to comply with various relevant constraints. Moreover, our proposed approach allows formulating these constraints using advanced model engineering techniques, such as scenario-based modeling. This mix of black-box learning-based tools with classical modeling approaches could produce systems that are effective and efficient, but are also more transparent and maintainable. We evaluated our technique using a case-study from the domain of internet congestion control, obtainin
g promising results.
(More)