Reinforcement Learning Augmented Optimization for Smart Mobility

被引:0
|
作者
Overko, Roman [1 ]
Ordonez-Hurtado, Rodrigo [2 ]
Zhuk, Sergiy [2 ]
Shorten, Robert [1 ]
机构
[1] Univ Coll Dublin, Dublin, Ireland
[2] IBM Res, Bldg 3,Damastown Ind Pk, Dublin 15, Ireland
来源
2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC) | 2019年
关键词
ALGORITHMS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Many mobility applications in smart cities are addressed as optimization problems. However, often, these problems are fragile due to their large-scale and non-convex nature, and also due to uncertainties arising because of human activity. In this paper, we apply a model-based Markov-decision-process (MDP) closed-loop identification algorithm to augment classical optimizers, with a view to alleviating this fragility. Specifically, we use deterministic optimal solutions provided by classical optimizers as initial guesses for MDP's policies, which are then "amended" as a result of online interaction with the environment to cope with uncertainty. Applications are described from niche of smart mobility problems, and numerical results are provided.
引用
收藏
页码:1286 / 1292
页数:7
相关论文
共 50 条
  • [21] Augmented learning, smart glasses and knowing how
    Wulf Loh
    Catrin Misselhorn
    AI & SOCIETY, 2020, 35 : 297 - 308
  • [22] Audio Augmented Reality in Smart Learning Environments
    Yao, Shu-Nung
    Liang, Chaoyun
    IEEE TRANSACTIONS ON LEARNING TECHNOLOGIES, 2023, 16 (02): : 178 - 190
  • [23] Augmented learning, smart glasses and knowing how
    Loh, Wulf
    Misselhorn, Catrin
    AI & SOCIETY, 2020, 35 (02) : 297 - 308
  • [24] Reinforcement Learning for Smart Charging of Electric Buses in Smart Grid
    Chen, Wenzhuo
    Zhuang, Peng
    Liang, Hao
    2019 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2019,
  • [25] A STOCHASTIC COMPOSITE AUGMENTED LAGRANGIAN METHOD FOR REINFORCEMENT LEARNING
    LI, Yongfeng
    Zhao, Mingming
    Chen, Weijie
    Wen, Zaiwen
    SIAM JOURNAL ON OPTIMIZATION, 2023, 33 (02) : 921 - 949
  • [26] Augmented Memory Replay in Reinforcement Learning With Continuous Control
    Ramicic, Mirza
    Bonarini, Andrea
    IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2022, 14 (02) : 485 - 496
  • [27] Self Organizing Networks: A Reinforcement Learning approach for self-optimization of LTE Mobility parameters
    Tiwana, Moazzam Islam
    AUTOMATIKA, 2014, 55 (04) : 504 - 513
  • [28] Predicting investment behavior: An augmented reinforcement learning model
    Shimokawa, Tetsuya
    Suzuki, Kyoko
    Misawa, Tadanobu
    Okano, Yoshitaka
    NEUROCOMPUTING, 2009, 72 (16-18) : 3447 - 3461
  • [29] Imagination-Augmented Agents for Deep Reinforcement Learning
    Racaniere, Sebastien
    Weber, Theophane
    Reichert, David P.
    Buesing, Lars
    Guez, Arthur
    Rezende, Danilo
    Badia, Adria Puigdomenech
    Vinyals, Oriol
    Heess, Nicolas
    Li, Yujia
    Pascanu, Razvan
    Battaglia, Peter
    Hassabis, Demis
    Silver, David
    Wierstra, Daan
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [30] Multitask Augmented Random Search in deep reinforcement learning
    Thanh, Le Tien
    Thang, Ta Bao
    Van Cuong, Le
    Binh, Huynh Thi Thanh
    APPLIED SOFT COMPUTING, 2024, 160