Scenario-Assisted Deep Reinforcement Learning

Raz Yerushalmi, Guy Amir, Achiya Elyasaf, David Harel, Guy Katz, Assaf Marron

Research output: Working paper/PreprintPreprint

20 Downloads (Pure)

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, obtaining promising results.
Original languageEnglish
StatePublished - 1 Feb 2022

Keywords

  • Computer Science - Machine Learning
  • Computer Science - Software Engineering
  • Electrical Engineering and Systems Science - Systems and Control

Fingerprint

Dive into the research topics of 'Scenario-Assisted Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this