Recently, several studies\citep {zhou2021nearly, zhang2021variance, kim2021improved,
zhou2022computationally} have provided variance-dependent regret bounds for linear …

We study linear contextual bandits in the misspecified setting, where the expected reward
function can be approximated by a linear function class up to a bounded misspecification …

learning with function approximation is one of the most empirically successful while
theoretically mysterious reinforcement learning (RL) algorithms and was identified in [RS …

We propose a new regret minimization algorithm for episodic sparse linear Markov decision
process (SMDP) where the state-transition distribution is a linear function of observed …

We study reinforcement learning for infinite-horizon discounted linear kernel MDPs, where
the transition probability function is linear in a predefined feature mapping. Existing …

We study the constrained Markov decision processes (CMDPs), in which an agent aims to
maximize the expected cumulative reward subject to a constraint on the expected total value …

Recently, there has been remarkable progress in reinforcement learning (RL) with general
function approximation. However, all these works only provide regret or sample complexity …

Existing performance measures for bandit algorithms such as regret, PAC bounds, or
uniform-PAC (Dann et al., 2017), typically evaluate the cumulative performance, while …

We study the constant regret guarantees in reinforcement learning (RL). Our objective is to
design an algorithm that incurs only finite regret over infinite episodes with high probability …

We investigate the non-stationary stochastic linear bandit problem where the reward
distribution evolves each round. Existing algorithms characterize the non-stationarity by the …