Multi-armed bandits a simple but very powerful framework for algorithms that make
decisions over time under uncertainty. An enormous body of work has accumulated over the …

Deep reinforcement learning has recorded remarkable performance in diverse application
areas of artificial intelligence: pattern recognition, robotics, object segmentation …

Multi-agent reinforcement learning (MARL) algorithms often suffer from an exponential
sample complexity dependence on the number of agents, a phenomenon known as the …

We consider a multi-armed bandit game where N players compete for K arms for T turns.
Each player has different expected rewards for the arms, and the instantaneous rewards are …

We formulate and study a decentralized multi-armed bandit (MAB) problem. There are M
distributed players competing for N independent arms. Each arm, when played, offers iid …

This paper considers the design of efficient strategies that allow cognitive users to choose
frequency bands to sense and access among multiple bands with unknown parameters …

We consider the following fundamental problem in the context of channelized dynamic
spectrum access. There are M secondary users and N¿ M orthogonal channels. Each …

This article studies a distributed multiarmed bandit problem with heterogeneous
observations of rewards. The problem is cooperatively solved by agents assuming each …

We study the explore-exploit tradeoff in distributed cooperative decision-making using the
context of the multiarmed bandit (MAB) problem. For the distributed cooperative MAB …

Online learning in a two-sided matching market, with demand side agents continuously
competing to be matched with supply side (arms), abstracts the complex interactions under …