Complex Model Transformations by Reinforcement Learning with Uncertain Human Guidance

TL;DR

This paper introduces a reinforcement learning framework for complex model transformations guided by uncertain human advice, improving efficiency in model-driven engineering tasks like synchronization and repair.

Contribution

It presents a novel RL-based approach that incorporates uncertain human guidance into the development of complex model transformation sequences.

Findings

Human guidance improves RL performance in complex tasks

The framework effectively maps user-defined transformations to RL primitives

Trade-offs between advice certainty and timeliness enhance RL outcomes

Abstract

Model-driven engineering problems often require complex model transformations (MTs), i.e., MTs that are chained in extensive sequences. Pertinent examples of such problems include model synchronization, automated model repair, and design space exploration. Manually developing complex MTs is an error-prone and often infeasible process. Reinforcement learning (RL) is an apt way to alleviate these issues. In RL, an autonomous agent explores the state space through trial and error to identify beneficial sequences of actions, such as MTs. However, RL methods exhibit performance issues in complex problems. In these situations, human guidance can be of high utility. In this paper, we present an approach and technical framework for developing complex MT sequences through RL, guided by potentially uncertain human advice. Our framework allows user-defined MTs to be mapped onto RL primitives, and executes them as RL programs to find optimal MT sequences. Our evaluation shows that human guidance, even if uncertain, substantially improves RL performance, and results in more efficient development of complex MTs. Through a trade-off between the certainty and timeliness of human advice, our method takes a step towards RL-driven human-in-the-loop engineering methods.