2022
DOI: 10.48550/arxiv.2205.00473
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

A Survey on Distributed Online Optimization and Game

Abstract: Decentralized online learning (DOL) has been increasingly researched in the last decade, mostly motivated by its wide applications in sensor networks, commercial buildings, robotics (e.g., decentralized target tracking and formation control), smart grids, deep learning, and so forth. In this problem, there are a network of agents who may be cooperative (i.e., decentralized online optimization) or noncooperative (i.e., online game) through local information exchanges, and the local cost function of each agent i… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
2

Relationship

2
0

Authors

Journals

citations
Cited by 2 publications
(4 citation statements)
references
References 84 publications
0
4
0
Order By: Relevance
“…where the superscript t stands for the iteration number, T is the time horizon, and 1 E is the indicator function with an event E. Generally speaking, the external regret measures the greatest regret for not playing actions a i 's, and the internal regret indicates the greatest regret for not swapping to action a ′ i when each time actually playing action a A i . Note that weighted external and internal regrets are also defined by adding a weight at each time t [226], and other regrets are considered as well in the literature, including swap regret [91] and several dynamic/static NE-based regrets [17], [227]- [230].…”
Section: A Zero-sum Normal-and Extensive-form Gamesmentioning
confidence: 99%
See 2 more Smart Citations
“…where the superscript t stands for the iteration number, T is the time horizon, and 1 E is the indicator function with an event E. Generally speaking, the external regret measures the greatest regret for not playing actions a i 's, and the internal regret indicates the greatest regret for not swapping to action a ′ i when each time actually playing action a A i . Note that weighted external and internal regrets are also defined by adding a weight at each time t [226], and other regrets are considered as well in the literature, including swap regret [91] and several dynamic/static NE-based regrets [17], [227]- [230].…”
Section: A Zero-sum Normal-and Extensive-form Gamesmentioning
confidence: 99%
“…Most of games have been investigated as static ones, i.e., with time-invariant game rules. However, due to possible dynamic characteristics of the environment within which players compete, online game (or time-varying game) is imperative for further attention in future, where each player's utility function is time-varying or even adversarial without any distribution assumptions [17], [227]- [230]. • Hybrid Games.…”
Section: Possible Future Directionsmentioning
confidence: 99%
See 1 more Smart Citation
“…Another performance indicator is fit, which measures the degree of violation of static/time-varying inequality constraints. For more details, a recent survey can be referenced [5].…”
Section: Introductionmentioning
confidence: 99%