Abstract Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed
dataset of transitions collected by another policy. This problem has attracted a lot of attention …

We study the problem of offline policy optimization in stochastic contextual bandit problems,
where the goal is to learn a near-optimal policy based on a dataset of decision data …

Stochastic multi-armed bandits are a sequential-decision-making framework, where, at each
interaction step, the learner selects an arm and observes a stochastic reward. Within the …

In this paper, we face the challenge of online learning in adversarial Markov decision
processes with off-policy feedback. In this setting, the learner chooses a policy, but …