On Distributed Multi-player Multiarmed Bandit Problems in Abruptly Changing Environment
This addresses distributed decision-making in dynamic settings for applications like wireless networks, though it appears incremental with new algorithms for a known bottleneck.
The paper tackles the multi-player multi-armed bandit problem in abruptly changing environments by designing two novel algorithms, RR-SW-UCB# and SW-DLP, and shows that their expected cumulative group regret is sublinear in time, asymptotically converging to zero.
We study the multi-player stochastic multiarmed bandit (MAB) problem in an abruptly changing environment. We consider a collision model in which a player receives reward at an arm if it is the only player to select the arm. We design two novel algorithms, namely, Round-Robin Sliding-Window Upper Confidence Bound\# (RR-SW-UCB\#), and the Sliding-Window Distributed Learning with Prioritization (SW-DLP). We rigorously analyze these algorithms and show that the expected cumulative group regret for these algorithms is upper bounded by sublinear functions of time, i.e., the time average of the regret asymptotically converges to zero. We complement our analytic results with numerical illustrations.