Zaiwei Chen

An Approximate Policy Iteration Viewpoint of Actor-Critic Algorithms

In this work, we consider policy-based methods for solving the reinforcement learning problem, and establish the sample complexity guarantees. A policy-based algorithm typically consists of an...

Two-Timescale Q-Learning with Function Approximation in Zero-Sum Stochastic Games

Maximizing the Value of Predictions in Control: Accuracy Is Not Enough

Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach

Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators

Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities

Non-Asymptotic Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes

Finite-Sample Analysis of Contractive Stochastic Approximation Using Smooth Convex Envelopes

A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games

Sample Complexity of Policy-Based Methods under Off-Policy Sampling and Linear Function Approximation

Approximate Global Convergence of Independent Learning in Multi-Agent Systems

Convergence rates for localized actor-critic in networked Markov potential games

Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning

A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies

Stationary Behavior of Constant Stepsize SGD Type Algorithms: An Asymptotic Characterization

Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm

Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization

Decentralized Best-Response-Based Learning in Two-Player Zero-Sum Stochastic Games: A Finite-Sample Analysis

We present a finite-sample analysis of decentralized learning in two-player zero-sum matrix games and stochastic games, with a focus on best-response-based learning algorithms. In matrix games,...