Logarithmic regret in communicating MDPs: Leveraging known dynamics with bandits.
Hassan Saber, Fabien Pesquerel, Odalric-Ambrym Maillard, Mohammad Sadegh Talebi
Browse the full ACML paper archive.
Hassan Saber, Fabien Pesquerel, Odalric-Ambrym Maillard, Mohammad Sadegh Talebi
Browse the full ACML paper archive.