Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control

被引:1
|
作者
Di Natale, Loris [1 ,2 ]
Svetozarevic, Bratislav [1 ]
Heer, Philipp [1 ]
Jones, Colin N. [2 ]
机构
[1] Urban Energy Syst Lab, Swiss Fed Labs Mat Sci & Technol Empa, CH-8600 Dubendorf, Switzerland
[2] Swiss Fed Inst Technol Lausanne EPFL, Lab Automat, CH-1015 Lausanne, Switzerland
基金
瑞士国家科学基金会;
关键词
D O I
10.1109/ICCA54724.2022.9831914
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Replacing poorly performing existing controllers with smarter solutions will decrease the energy intensity of the building sector. Recently, controllers based on Deep Reinforcement Learning (DRL) have been shown to be more effective than conventional baselines. However, since the optimal solution is usually unknown, it is still unclear if DRL agents are attaining near-optimal performance in general or if there is still a large gap to bridge. In this paper, we investigate the performance of DRL agents compared to the theoretically optimal solution. To that end, we leverage Physically Consistent Neural Networks (PCNNs) as simulation environments, for which optimal control inputs are easy to compute. Furthermore, PCNNs solely rely on data to be trained, avoiding the difficult physics-based modeling phase, while retaining physical consistency. Our results hint that DRL agents not only clearly outperform conventional rule-based controllers, they furthermore attain near-optimal performance.
引用
收藏
页码:698 / 703
页数:6
相关论文
共 50 条
  • [41] Optimal, near-optimal, and robust epidemic control
    Morris, Dylan H.
    Rossine, Fernando W.
    Plotkin, Joshua B.
    Levin, Simon A.
    COMMUNICATIONS PHYSICS, 2021, 4 (01)
  • [42] Safe Learning for Near-Optimal Scheduling
    Busatto-Gaston, Damien
    Chakraborty, Debraj
    Guha, Shibashis
    Perez, Guillermo A.
    Raskin, Jean-Francois
    QUANTITATIVE EVALUATION OF SYSTEMS (QEST 2021), 2021, 12846 : 235 - 254
  • [43] Near-Optimal Collaborative Learning in Bandits
    Reda, Clemence
    Vakili, Sattar
    Kaufmann, Emilie
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [44] A Hierarchy of Near-Optimal Policies for Multistage Adaptive Optimization
    Bertsimas, Dimitris
    Iancu, Dan Andrei
    Parrilo, Pablo A.
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2011, 56 (12) : 2803 - 2818
  • [45] Application of a Near-Optimal Reinforcement Learning Controller to a Robotics Problem in Manufacturing: A Hybrid Approach
    Warren E. Hearnes
    Augustine O. Esogbue
    Fuzzy Optimization and Decision Making, 2003, 2 (3) : 183 - 213
  • [46] Faster near-optimal reinforcement learning:: Adding adaptiveness to the E3 algorithm
    Domingo, C
    ALGORITHMIC LEARNING THEORY, PROCEEDINGS, 1999, 1720 : 241 - 251
  • [47] Response of near-optimal agricultural production to water policies
    Amir, I
    Fisher, FM
    AGRICULTURAL SYSTEMS, 2000, 64 (02) : 115 - 130
  • [48] Computing Near-Optimal Policies in Generalized Joint Replenishment
    Adelman, Daniel
    Klabjan, Diego
    INFORMS JOURNAL ON COMPUTING, 2012, 24 (01) : 148 - 164
  • [49] Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments
    Chen, Liyu
    Luo, Haipeng
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,
  • [50] Reinforcement Learning for Near-Optimal Design of Zero-Delay Codes for Markov Sources
    Cregg, Liam
    Linder, Tamas
    Yuksel, Serdar
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2024, 70 (11) : 8399 - 8413