Fig. 6From: A multi-armed bandit approach for exploring partially observed networksInvestigating non-stationarity of the environment. Compares the number of nodes observed by our proposed algorithm with different values of sliding window τ. When τ=1000, all the observations are used by the k-NN regression. Each graph corresponds to a LFR benchmark network generated with the corresponding mixing parameter μ. Results indicate the average of 10 independently sampled partially observed networksBack to article page