Offline-online reinforcement learning for generalizing demand response price-setting to energy systems

Doseok Jang, Lucas Spangher, Manan Khattar, Utkarsha Agwan, Selvaprabuh Nadarajah, Costas J. Spanos

Abstract: Our team is proposing to run a full-scale energy demand response experiment in an office building. Although this is an exciting endeavor, collecting training data for the reinforcement learning agent is costly and will be limited. In this work, we examine how offline training can be leveraged to minimize data costs (accelerate convergence) and program implementation costs by pretraining our model to warm start the experiment with simulated tasks. We present results that demonstrate the utility of offline reinforcement learning to efficient price-setting in the energy demand response problem.