Recent studies in reinforcement learning (RL) have made significant progress by leveraging
function approximation to alleviate the sample complexity hurdle for better performance …

This paper studies a cooperative multi-armed bandit problem with $ M $ agents cooperating
together to solve the same instance of a $ K $-armed stochastic bandit problem with the goal …

The standard assumption in reinforcement learning (RL) is that agents observe feedback for
their actions immediately. However, in practice feedback is often observed in delay. This …

Abstract We propose Banker Online Mirror Descent (Banker-OMD), a novel framework
generalizing the classical Online Mirror Descent (OMD) technique in the online learning …

Policy Optimization (PO) is one of the most popular methods in Reinforcement Learning
(RL). Thus, theoretical guarantees for PO algorithms have become especially important to …

We study stochastic delayed feedback in general single-agent and multi-agent sequential
decision making, which includes bandits, single-agent Markov decision processes (MDPs) …

The growing interest in complex decision-making and language modeling problems
highlights the importance of sample-efficient learning over very long horizons. This work …

We propose novel algorithms with first-and second-order regret bounds for adversarial
linear bandits. These regret bounds imply that our algorithms perform well when there is an …

In many real-world sequential decision-making problems, an action does not immediately
reflect on the feedback and spreads its effects over a long time frame. For instance, in online …

We derive a new analysis of Follow The Regularized Leader (FTRL) for online learning with
delayed bandit feedback. By separating the cost of delayed feedback from that of bandit …