Continual Reinforcement Learning Formulation for Zero-Sum Game-Based Constrained Optimal Tracking

Behzad Farzanegan; Sarangapani Jagannathan; Jagannathan Sarangapani

doi:10.1109/TSMC.2023.3299556

Continual Reinforcement Learning Formulation for Zero-Sum Game-Based Constrained Optimal Tracking

Behzad Farzanegan
, Sarangapani Jagannathan
, Jagannathan Sarangapani

Missouri University of Science and Technology

Research output: Contribution to journal › Article › peer-review

Original language	English
Pages (from-to)	7744-7757
Number of pages	14
Journal	IEEE Transactions on Systems, Man, and Cybernetics: Systems
Volume	53
Issue number	12
DOIs	https://doi.org/10.1109/TSMC.2023.3299556
State	Published - Dec 1 2023

ASJC Scopus Subject Areas

Software
Control and Systems Engineering
Human-Computer Interaction
Computer Science Applications
Electrical and Electronic Engineering

Keywords

Barrier Lyapunov function
experience replay
hybrid learning
lifelong learning
optimal tracking control
safety
zero-sum game (ZSG)

Access to Document

10.1109/TSMC.2023.3299556

Cite this

@article{50a5ae6505bf4ae7b25a9abf16005d9e,

title = "Continual Reinforcement Learning Formulation for Zero-Sum Game-Based Constrained Optimal Tracking",

keywords = "Barrier Lyapunov function, experience replay, hybrid learning, lifelong learning, optimal tracking control, safety, zero-sum game (ZSG)",

author = "Behzad Farzanegan and Sarangapani Jagannathan and Jagannathan Sarangapani",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2023",

month = dec,

day = "1",

doi = "10.1109/TSMC.2023.3299556",

language = "English",

volume = "53",

pages = "7744--7757",

journal = "IEEE Transactions on Systems, Man, and Cybernetics: Systems",

issn = "2168-2216",

number = "12",

}

TY - JOUR

T1 - Continual Reinforcement Learning Formulation for Zero-Sum Game-Based Constrained Optimal Tracking

AU - Farzanegan, Behzad

AU - Jagannathan, Sarangapani

AU - Sarangapani, Jagannathan

PY - 2023/12/1

Y1 - 2023/12/1

KW - Barrier Lyapunov function

KW - experience replay

KW - hybrid learning

KW - lifelong learning

KW - optimal tracking control

KW - safety

KW - zero-sum game (ZSG)

UR - https://www.scopus.com/pages/publications/85168271983

UR - https://www.scopus.com/pages/publications/85168271983#tab=citedBy

U2 - 10.1109/TSMC.2023.3299556

DO - 10.1109/TSMC.2023.3299556

M3 - Article

SN - 2168-2216

VL - 53

SP - 7744

EP - 7757

JO - IEEE Transactions on Systems, Man, and Cybernetics: Systems

JF - IEEE Transactions on Systems, Man, and Cybernetics: Systems

IS - 12

ER -

Continual Reinforcement Learning Formulation for Zero-Sum Game-Based Constrained Optimal Tracking

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this