Towards a Domain-Specific Modelling Environment for Reinforcement Learning

TL;DR

This paper presents a domain-specific modelling environment for reinforcement learning that simplifies the development process through a specialized language and supporting tools, making RL more accessible.

Contribution

It introduces RLML, a new modeling language for reinforcement learning, with tools for syntax checking, code generation, and result comparison, enhancing usability and understanding.

Findings

Improved abstraction of reinforcement learning technologies.

Enhanced user experience with syntax-directed editing and constraint checking.

Facilitated comparison of multiple RL algorithms.

Abstract

In recent years, machine learning technologies have gained immense popularity and are being used in a wide range of domains. However, due to the complexity associated with machine learning algorithms, it is a challenge to make it user-friendly, easy to understand and apply. Machine learning applications are especially challenging for users who do not have proficiency in this area. In this paper, we use model-driven engineering (MDE) methods and tools for developing a domain-specific modelling environment to contribute towards providing a solution for this problem. We targeted reinforcement learning from the machine learning domain, and evaluated the proposed language, reinforcement learning modelling language (RLML), with multiple applications. The tool supports syntax-directed editing, constraint checking, and automatic generation of code from RLML models. The environment also provides support for comparing results generated with multiple RL algorithms. With our proposed MDE approach, we were able to help in abstracting reinforcement learning technologies and improve the learning curve for RL users.