Planning with tensor networks based on active inference

被引：0
|
作者：
Wauthier, Samuel T. [1 ]
Verbelen, Tim [2 ]
Dhoedt, Bart [1 ]
Vanhecke, Bram [3 ]
机构：
[1] IDLab, Department of Information Technology, Ghent University—imec, Technologiepark-Zwijnaarde 126, Ghent,B-9052, Belgium
[2] VERSES AI Research Lab, Los Angeles,CA,90016, United States
[3] Faculty of Physics, Faculty of Mathematics, Quantum Optics, Quantum Nanophysics and Quantum Information, University of Vienna, Boltzmanngasse 5, Vienna,1090, Austria
来源：
Machine Learning: Science and Technology | 2024年 / 5卷 / 04期
关键词：
Tensor networks (TNs) have seen an increase in applications in recent years. While they were originally developed to model many-body quantum systems; their usage has expanded into the field of machine learning. This work adds to the growing range of applications by focusing on planning by combining the generative modeling capabilities of matrix product states and the action selection algorithm provided by active inference. Their ability to deal with the curse of dimensionality; to represent probability distributions; and to dynamically discover hidden variables make matrix product states specifically an interesting choice to use as the generative model in active inference; which relies on ‘beliefs’ about hidden states within an environment. We evaluate our method on the T-maze and Frozen Lake environments; and show that the TN-based agent acts Bayes optimally as expected under active inference. © 2024 The Author(s). Published by IOP Publishing Ltd;
D O I：
10.1088/2632-2153/ad7571
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 50 条
  • [21] Reliability-Based Expansion Planning Studies of Active Distribution Networks With Multiagents
    Kabirifar, Milad
    Fotuhi-Firuzabad, Mahmud
    Moeini-Aghtaie, Moein
    Pourghaderi, Niloofar
    Shahidehpour, Mohammad
    IEEE TRANSACTIONS ON SMART GRID, 2022, 13 (06) : 4610 - 4623
  • [22] THE INFERENCE OF HUMAN RESOURCE PLANNING OPERATION USING BAYESIAN NETWORKS
    Kataoka, Takayuki
    Kanezashi, Masakazu
    Morikawa, Katsumi
    Takahashi, Katsuhiko
    ICIM 2010: PROCEEDINGS OF THE TENTH INTERNATIONAL CONFERENCE ON INDUSTRIAL MANAGEMENT, 2010, : 537 - +
  • [23] Intelligent Resource Allocation for UAV-Based Cognitive NOMA Networks: An Active Inference Approach
    Obite, Felix
    Krayani, Ali
    Alam, Atm S.
    Marcenaro, Lucio
    Nallanathan, Arumugam
    Regazzoni, Carlo
    2023 IEEE FUTURE NETWORKS WORLD FORUM, FNWF, 2024,
  • [24] Multistage Coordinated Planning of Active Distribution Networks
    Koutsoukis, Nikolaos C.
    Georgilakis, Pavlos S.
    Hatziargyriou, Nikos D.
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2018, 33 (01) : 32 - 44
  • [25] Active Inference and Behavior Trees for Reactive Action Planning and Execution in Robotics
    Pezzato, Corrado
    Corbato, Carlos Hernandez
    Bonhof, Stefan
    Wisse, Martijn
    IEEE TRANSACTIONS ON ROBOTICS, 2023, 39 (02) : 1050 - 1069
  • [26] Active inference for dynamic Bayesian networks with an application to tissue engineering
    Caner Komurlu
    Jinjian Shao
    Banu Akar
    Elif S. Bayrak
    Eric M. Brey
    Ali Cinar
    Mustafa Bilgic
    Knowledge and Information Systems, 2017, 50 : 917 - 943
  • [27] Active inference for dynamic Bayesian networks with an application to tissue engineering
    Komurlu, Caner
    Shao, Jinjian
    Akar, Banu
    Bayrak, Elif S.
    Brey, Eric M.
    Cinar, Ali
    Bilgic, Mustafa
    KNOWLEDGE AND INFORMATION SYSTEMS, 2017, 50 (03) : 917 - 943
  • [28] TENSOR VECTOR FIELD BASED ACTIVE CONTOURS
    Kumar, Abhishek
    Wong, Alexander
    Mishra, Akshaya
    Clausi, David A.
    Fieguth, Paul
    2011 18TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2011,
  • [29] Tensor-Based Active Appearance Model
    Lee, Hyung-Soo
    Kim, Daijin
    IEEE SIGNAL PROCESSING LETTERS, 2008, 15 : 565 - 568
  • [30] Active thermography based on tensor rank decomposition
    Spaeth, Peter W.
    Takunju, Peter L.
    Zalameda, Joseph N.
    THERMOSENSE: THERMAL INFRARED APPLICATIONS XLIV, 2022, 12109
12345