In a multi-armed bandit (MAB) problem a gambler needs to choose at each round of play
one of K arms, each characterized by an unknown reward distribution. Reward realizations …

We introduce algorithms that achieve state-of-the-art dynamic regret bounds for non-
stationary linear stochastic bandit setting. It captures natural applications such as dynamic …

We consider un-discounted reinforcement learning (RL) in Markov decision processes
(MDPs) under drifting non-stationarity,\ie, both the reward and state transition distributions …

We propose the first contextual bandit algorithm that is parameter-free, efficient, and optimal
in terms of dynamic regret. Specifically, our algorithm achieves $\mathcal {O}(\min\{\sqrt …

We consider model-free reinforcement learning (RL) in non-stationary Markov decision
processes. Both the reward functions and the state transition functions are allowed to vary …

We introduce data-driven decision-making algorithms that achieve state-of-the-art dynamic
regret bounds for a collection of nonstationary stochastic bandit settings. These settings …

Most contextual bandit algorithms minimize regret against the best fixed policy, a
questionable benchmark for non-stationary environments that are ubiquitous in applications …

We consider reinforcement learning (RL) in episodic MDPs with adversarial full-information
reward feedback and unknown fixed transition kernels. We propose two model-free policy …

Experimentation has been critical and increasingly popular across various domains, such as
clinical trials and online platforms, due to its widely recognized benefits. One of the primary …

General function approximation is a powerful tool to handle large state and action spaces in
a broad range of reinforcement learning (RL) scenarios. However, theoretical understanding …