Implementation of TV-KL-UCB and other multi-armed bandit algorithms for rested Markovian bandits. The details of these algorithms can be found here: https://arxiv.org/abs/2009.06606
Implementation of TV-KL-UCB and other multi-armed bandit algorithms for rested Markovian bandits. The details of these algorithms can be found here: https://arxiv.org/abs/2009.06606