Learning to Optimise Climate Sensor Placement using a Transformer

TL;DR

This paper introduces a deep reinforcement learning approach using actor-critic algorithms to improve climate sensor placement, outperforming traditional heuristic methods in generating high-quality solutions.

Contribution

It presents a novel RL-based method for sensor placement that automates heuristic generation, surpassing existing approaches in effectiveness.

Findings

Our method outperforms state-of-the-art approaches in solution quality.

Deep RL effectively learns improvement heuristics for sensor placement.

The approach demonstrates robustness across various experimental scenarios.

Abstract

The optimal placement of sensors for environmental monitoring and disaster management is a challenging problem due to its NP-hard nature. Traditional methods for sensor placement involve exact, approximation, or heuristic approaches, with the latter being the most widely used. However, heuristic methods are limited by expert intuition and experience. Deep learning (DL) has emerged as a promising approach for generating heuristic algorithms automatically. In this paper, we introduce a novel sensor placement approach focused on learning improvement heuristics using deep reinforcement learning (RL) methods. Our approach leverages an RL formulation for learning improvement heuristics, driven by an actor-critic algorithm for training the policy network. We compare our method with several state-of-the-art approaches by conducting comprehensive experiments, demonstrating the effectiveness and superiority of our proposed approach in producing high-quality solutions. Our work presents a promising direction for applying advanced DL and RL techniques to challenging climate sensor placement problems.