Transfer in Sequential Multi-armed Bandits via Reward Samples

arXiv:2403.12428v1 Announce Type: new
Abstract: We consider a sequential stochastic multi-armed bandit problem where the agent interacts with bandit over multiple episodes. The reward distribution of the arms remain constant throughout an episode but can change over different episodes. We propose an algorithm based on UCB to transfer the reward samples from the previous episodes and improve the cumulative regret performance over all the episodes. We provide regret analysis and empirical results for our algorithm, which show significant improvement over …

abstract agent algorithm arxiv change cs.lg distribution episodes multi-armed bandits multiple samples stat.ml stochastic transfer type via