The rapid changes in the finance industry due to the increasing amount of data have
revolutionized the techniques on data processing and data analysis and brought new …

Abstract Modern Reinforcement Learning (RL) is commonly applied to practical problems
with an enormous number of states, where\emph {function approximation} must be deployed …

This paper studies model-based reinforcement learning (RL) for regret minimization. We
focus on finite-horizon episodic RL where the transition model $ P $ belongs to a known …

In order to deal with the curse of dimensionality in reinforcement learning (RL), it is common
practice to make parametric assumptions where values or policies are functions of some low …

This work studies the question of Representation Learning in RL: how can we learn a
compact low-dimensional representation such that on top of the representation we can …

We study model-based offline Reinforcement Learning with general function approximation
without a full coverage assumption on the offline data distribution. We present an algorithm …

We study reinforcement learning (RL) with linear function approximation where the
underlying transition probability kernel of the Markov decision process (MDP) is a linear …

While policy-based reinforcement learning (RL) achieves tremendous successes in practice,
it is significantly less understood in theory, especially compared with value-based RL. In …

Actor-critic methods are widely used in offline reinforcement learningpractice, but are not so
well-understood theoretically. We propose a newoffline actor-critic algorithm that naturally …

We study the stochastic contextual bandit problem, where the reward is generated from an
unknown function with additive noise. No assumption is made about the reward function …