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
  • [21] Near-Optimal Sparse Allreduce for Distributed Deep Learning
    Li, Shigang
    Hoefler, Torsten
    PPOPP'22: PROCEEDINGS OF THE 27TH ACM SIGPLAN SYMPOSIUM ON PRINCIPLES AND PRACTICE OF PARALLEL PROGRAMMING, 2022, : 135 - 149
  • [22] Kernel-based multiagent reinforcement learning for near-optimal formation control of mobile robots
    Ronghua Zhang
    Xin Xu
    Xinglong Zhang
    Quan Xiong
    Qingwen Ma
    Yaoqian Peng
    Applied Intelligence, 2023, 53 : 12736 - 12748
  • [23] REPLACEMENT POLICIES - A NEAR-OPTIMAL ALGORITHM
    JAYABALAN, V
    CHAUDHURI, D
    IIE TRANSACTIONS, 1995, 27 (06) : 784 - 788
  • [24] A reinforcement learning-based near-optimal hierarchical approach for motion control: Design and experiment
    Qin, Zhi-Chang
    Zhu, Hai-Tao
    Wang, Shou-Jun
    Xin, Ying
    Sun, Jian-Qiao
    ISA TRANSACTIONS, 2022, 129 : 673 - 683
  • [25] Kernel-based multiagent reinforcement learning for near-optimal formation control of mobile robots
    Zhang, Ronghua
    Xu, Xin
    Zhang, Xinglong
    Xiong, Quan
    Ma, Qingwen
    Peng, Yaoqian
    APPLIED INTELLIGENCE, 2023, 53 (10) : 12736 - 12748
  • [26] Tractable near-optimal policies for crawling
    Azar, Yossi
    Horvitz, Eric
    Lubetzky, Eyal
    Peres, Yuval
    Shahaf, Dafna
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2018, 115 (32) : 8099 - 8103
  • [27] NEAR-OPTIMAL CONTROL OF PLANTS FROM INPUT-OUTPUT DATA
    GENESIO, R
    POME, R
    INTERNATIONAL JOURNAL OF CONTROL, 1974, 20 (02) : 335 - 346
  • [28] DEEP REINFORCEMENT LEARNING FOR TRANSFER OF CONTROL POLICIES
    Cunningham, James D.
    Miller, Simon W.
    Yukish, Michael A.
    Simpson, Timothy W.
    Tucker, Conrad S.
    PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2019, VOL 2A, 2020,
  • [29] COMPUTATION OF THE NEAR-OPTIMAL TEMPERATURE AND INITIATOR POLICIES FOR A BATCH POLYMERIZATION REACTOR
    THOMAS, IM
    KIPARISSIDES, C
    CANADIAN JOURNAL OF CHEMICAL ENGINEERING, 1984, 62 (02): : 284 - 291
  • [30] Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning
    Zhang, Zihan
    Jiang, Yuhang
    Zhou, Yuan
    Ji, Xiangyang
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022, 2022,