Decision-making in the face of uncertainty is a significant challenge in machine learning,
and the multi-armed bandit model is a commonly used framework to address it. This …

Any reinforcement learning algorithm that applies to all Markov decision processes (MDPs)
will suffer $\Omega (\sqrt {SAT}) $ regret on some MDP, where $ T $ is the elapsed time and …

We integrate information-theoretic concepts into the design and analysis of optimistic
algorithms and Thompson sampling. By making a connection between information-theoretic …

In this paper, we investigate Nash-regret minimization in congestion games, a class of
games with benign theoretical structure and broad real-world applications. We first propose …

We investigate a condition-based group maintenance problem for multi-component systems,
where the degradation process of a specific component is affected only by its neighbouring …

We study minimax optimal reinforcement learning in episodic factored Markov decision
processes (FMDPs), which are MDPs with conditionally independent transition components …

We study regret minimization in non-episodic factored Markov decision processes (FMDPs),
where all existing algorithms make the strong assumption that the factored structure of the …

Concisely defined, Reinforcement Learning, abbreviated as RL, is the discipline of learning
and acting in environments where sequential decisions are made. That is, the decision …

We consider a regret minimization task under the average-reward criterion in an unknown
Factored Markov Decision Process (FMDP). More specifically, we consider an FMDP where …

We consider provably-efficient reinforcement learning (RL) in non-episodic factored Markov
decision processes (FMDPs). All previous algorithms for regret minimization in this setting …