File Exchange

image thumbnail

Covariance matrix adaptation for multi-objective multi-armed

version 1.0.1 by Madalina Drugan
source code for the article

Updated 22 Jan 2019

Upper confidence bound (UCB) is a successful multiarmed bandit for regret minimization. The covariance matrix adaptation (CMA) for Pareto UCB (CMA-PUCB) algorithm considers stochastic reward vectors with correlated objectives. We upper bound the cumulative pseudoregret of pulling suboptimal arms for the CMA-PUCB algorithm to logarithmic number of arms K, objectives D, and samples n, O(ln(nDK) ∑i (||Σi||²/Δi)), using a variant of Berstein inequality for matrices, where Δi is the regret of pulling the suboptimal arm i. For unknown covariance matrices between objectives Σi, we upper bound the approximation of the covariance matrix using the number of samples to O(nln(nDK) + ln²(nDK) ∑i (1/Δi)). Simulations on a three objective stochastic environment show the applicability of our method.

Cite As

M. “Covariance Matrix Adaptation for Multiobjective Multiarmed Bandits.” IEEE Transactions on Neural Networks and Learning Systems, Institute of Electrical and Electronics Engineers (IEEE), 2018, pp. 1–10, doi:10.1109/tnnls.2018.2885123.

View more styles

Comments and Ratings (0)

Updates

1.0.1

Update link

MATLAB Release Compatibility
Created with R2018b
Compatible with any release
Platform Compatibility
Windows macOS Linux