Networks of Learning Automata: Techniques for Online Stochastic Optimization

By M. Thathachar, P. Shanti Sastry. 2003

364 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/951cf0285a158bc11caa4711896c6f2d7b0e91b0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Exploiting structure and utilizing agent-centric rewards to promote coordination in large multiagent systems (2013, methodology): “This work uses FALA as a second learning mechanism and adopts the linear reward-inaction(LR−I) algorithm as our update mechanism [36].”
Complete Random Forest Based Class Noise Filtering Learning for Improving the Generalizability of Classifiers (2019, background): “The least squares loss is also robust to the uniform class noise, which ensures the robustness of the Fisher linear discriminant for a particular case [18].”
Noise Tolerance Under Risk Minimization (2011, background): “(The fact that risk minimization under 0–1 loss function is tolerant to uniform noise is known earlier (see, e.g. [9, chap 4])) For the second part of the theorem, η is no longer constant but we assume R ( f ∗ ) = 0 .”
Exploiting Structure and Agent-Centric Rewards to Promote Coordination in Large Multiagent Systems (2014, methodology): “This work uses FALA as a second learning mechanism and adopts the linear reward-inaction(LR−I) algorithm as our update mechanism [36].”
Classification in the Presence of Label Noise: A Survey (2014, background): “It is demonstrated that the 0-1 loss is label noise-robust for uniform label noise [140] or when it is possible to achieve zero error rate [81]; see e.g. [74] for a discussion in the case of NNAR label noise.”
Solving two-armed Bernoulli bandit problems using a Bayesian learning automaton (2010, methodology): “…its advantages over established top performers from two distinct research areas, namely, learning automata (LA) and Bandit playing algorithms (see Thathachar and Sastry (2004), Narendra and Thathachar (1989) and Vermorel and Mohri (2005), respectively, for an overview of current algorithms).”