Scenario-Assisted Deep Reinforcement Learning

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.

A new deep Q-learning method with dynamic epsilon adjustment and path planner assisted techniques for Turtlebot mobile robot

“…In 2022, Raz et al 2 developed a Scenario-Assisted Deep Reinforcement Learning technique for enhancing the reinforcement learning training process, which allowed engineers to directly contribute their domain knowledge, making the agent under training more likely to comply with various relevant constraints. The authors modified the reward calculation based on the constraints relevant to internet traffic control domain knowledge.…”