Abstract We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new
algorithm for reinforcement learning in tabular and possibly stage-dependent, episodic …

We consider reinforcement learning in an environment modeled by an episodic, tabular,
step-dependent Markov decision process of horizon $ H $ with $ S $ states, and $ A …

In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to
identify an $\epsilon $-optimal policy with probability $1-\delta $. While minimax optimal …

We consider the problem of quantifying uncertainty over expected cumulative rewards in
model-based reinforcement learning. In particular, we focus on characterizing the variance …

In this paper, we introduce Randomized Q-learning (RandQL), a novel randomized model-
free algorithm for regret minimization in episodic Markov Decision Processes (MDPs). To the …

Quantifying uncertainty about a policy's long-term performance is important to solve
sequential decision-making tasks. We study the problem from a model-based Bayesian …

Reinforcement learning (RL) has exceeded human performance in many synthetic settings
such as video games and Go. However, real-world deployment of end-to-end RL models is …

We study the corrupted bandit problem, ie a stochastic multi-armed bandit problem with $ k $
unknown reward distributions, which are heavy-tailed and corrupted by a history …

Online Reinforcement learning (RL) typically requires high-stakes online interaction data to
learn a policy for a target task. This prompts interest in leveraging historical data to improve …

We consider the problem of quantifying uncertainty over expected cumulative rewards in
model-based reinforcement learning. In particular, we focus on characterizing the variance …