Hierarchical reinforcement learning with OMQ

被引：0
|
作者：
Shen, Jing [1 ]
Liu, Haibo [1 ]
Gu, Guochang [1 ]
机构：
[1] Harbin Engn Univ, Sch Comp Sci & Technol, Harbin 150001, Peoples R China
来源：
PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON COGNITIVE INFORMATICS, VOLS 1 AND 2 | 2006年
关键词：
hierarchical reinforcement learning; Option; MAXQ;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A novel method of hierarchical reinforcement learning, named OMQ, by integrating Options into MAXQ is presented In OMQ, the MAXQ is used as basic framework to design hierarchies experientially and learn online, and the Option is used to construct hierarchies automatically. The performance of OMQ is demonstrated in taxi domain and compared with Option and MAXQ. The simulation results show that the OMQ is more practical than Option and MAXQ in partial known environment.
引用
收藏
页码：584 / 588
页数：5
相关论文
共 50 条
  • [1] Concurrent Hierarchical Reinforcement Learning
    Marthi, Bhaskara
    Russell, Stuart
    Latham, David
    Guestrin, Carlos
    19TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-05), 2005, : 779 - 785
  • [2] Hierarchical Imitation and Reinforcement Learning
    Le, Hoang M.
    Jiang, Nan
    Agarwal, Alekh
    Dudik, Miroslav
    Yue, Yisong
    Daume, Hal, III
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
  • [3] On Efficiency in Hierarchical Reinforcement Learning
    Wen, Zheng
    Precup, Doina
    Ibrahimi, Morteza
    Barreto, Andre
    Van Roy, Benjamin
    Singh, Satinder
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
  • [4] Budgeted Hierarchical Reinforcement Learning
    Leon, Aurelia
    Denoyer, Ludovic
    2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
  • [5] Hierarchical Reinforcement Learning: A Comprehensive Survey
    Pateria, Shubham
    Subagdja, Budhitama
    Tan, Ah-hwee
    Quek, Chai
    ACM COMPUTING SURVEYS, 2021, 54 (05)
  • [6] Deep Reinforcement Learning with Hierarchical Structures
    Li, Siyuan
    PROCEEDINGS OF THE THIRTIETH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2021, 2021, : 4899 - 4900
  • [7] Hierarchical average reward reinforcement learning
    Ghavamzadeh, Mohammad
    Mahadevan, Sridhar
    JOURNAL OF MACHINE LEARNING RESEARCH, 2007, 8 : 2629 - 2669
  • [8] Hierarchical reinforcement learning for biped locomotion
    Sugimoto, Norikazu
    Hyon, Sang-Ho
    Morimoto, Jun
    NEUROSCIENCE RESEARCH, 2009, 65 : S183 - S183
  • [9] FeUdal Networks for Hierarchical Reinforcement Learning
    Vezhnevets, Alexander Sasha
    Osindero, Simon
    Schaul, Tom
    Heess, Nicolas
    Jaderberg, Max
    Silver, David
    Kavukcuoglu, Koray
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
  • [10] Recent advances in hierarchical reinforcement learning
    Barto, AG
    Mahadevan, S
    DISCRETE EVENT DYNAMIC SYSTEMS-THEORY AND APPLICATIONS, 2003, 13 (04): : 343 - 379
12345