Since reinforcement learning algorithms are notoriously data-intensive, the task of sampling
observations from the environment is usually split across multiple agents. However …

The actor-critic (AC) algorithm is a popular method to find an optimal policy in reinforcement
learning. In the infinite horizon scenario, the finite-sample convergence rate for the AC and …

We present GradientDICE for estimating the density ratio between the state distribution of
the target policy and the sampling distribution in off-policy reinforcement learning …

The deadly triad refers to the instability of a reinforcement learning algorithm when it
employs off-policy learning, function approximation, and bootstrapping simultaneously. In …

This paper studies the performative prediction problem which optimizes a stochastic loss
function with data distribution that depends on the decision variable. We consider a setting …

Actor–critic style two-time-scale algorithms are one of the most popular methods in
reinforcement learning, and have seen great empirical success. However, their performance …

In this paper, we provide finite-sample convergence guarantees for an off-policy variant of
the natural actor-critic (NAC) algorithm based on Importance Sampling. In particular, we …

In this letter, we develop a novel variant of natural actor-critic algorithm using off-policy
sampling and linear function approximation, and establish a sample complexity of …

We consider off-policy policy evaluation with function approximation (FA) in average-reward
MDPs, where the goal is to estimate both the reward rate and the differential value function …

Actor-critic methods have achieved significant success in many challenging applications.
However, its finite-time convergence is still poorly understood in the most practical single …