scientific article; zbMATH DE number 7049736
From MaRDI portal
Publication:4633026
zbMath1483.68418arXiv1602.04741MaRDI QIDQ4633026
Nicolò Cesa-Bianchi, Claudio Gentile, Yishay Mansour
Publication date: 2 May 2019
Full work available at URL: https://arxiv.org/abs/1602.04741
Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.
regret minimizationmulti-armed banditsdistributed learningcooperative multi-agent systemsLOCAL communication
Learning and adaptive systems in artificial intelligence (68T05) Distributed algorithms (68W15) Agent technology and artificial intelligence (68T42)
Cites Work
- Competitive collaborative learning
- Independence and average distance in graphs
- Distributed cooperative decision making in multi-agent multi-armed bandits
- Survey of local algorithms
- Online Markov Decision Processes Under Bandit Feedback
- Locality in Distributed Graph Algorithms
- Distributed Online Learning via Cooperative Contextual Bandits
- Perturbed Iterate Analysis for Asynchronous Stochastic Optimization
- Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback
- On delayed prediction of individual sequences
- The Nonstochastic Multiarmed Bandit Problem
- Multiplicative updates outperform generic no-regret learning in congestion games
- Algorithmic Learning Theory
- An Asynchronous Parallel Stochastic Coordinate Descent Algorithm
- Finite-time analysis of the multiarmed bandit problem
This page was built for publication:
