Near-Optimal First-Order Regret for Bandits with Feedback Graphs
An algorithm for the special case of self-aware graphs, in which every vertex has a self-loop and a map whose fixed points yield sampling distributions that control the one-round regret remainder in terms of the learner's loss and the graph's independence number is constructed.
Meng-Xiao Zhang, Yu-Heng Zhang, Hai-Peng Luo et al.
· 0 citations