Reinforcement learning (RL) problems over general state and action spaces are notoriously
challenging. In contrast to the tableau setting, one can not enumerate all the states and then …

Explicit exploration in the action space was assumed to be indispensable for online policy
gradient methods to avoid a drastic degradation in sample complexity, for solving general …

We study average-reward Markov decision processes (AMDPs) and develop novel first-
order methods with strong theoretical guarantees for both policy optimization and policy …

We show that the stochastic gradient bandit algorithm converges to a globally optimal policy
at an $ O (1/t) $ rate, even with a constant step size. Remarkably, global convergence of the …

Federated reinforcement learning (RL) enables collaborative decision making of multiple
distributed agents without sharing local data trajectories. In this work, we consider a multi …

We propose Dual Approximation Policy Optimization (DAPO), a framework that incorporates
general function approximation into policy mirror descent methods. In contrast to the popular …

Policy gradient methods, where one searches for the policy of interest by maximizing the
value functions using first-order information, become increasingly popular for sequential …

In this short note, we give the convergence analysis of the policy in the recent famous policy
mirror descent (PMD). We mainly consider the unregularized setting following [11] with …

Linear programming (LP)[26, 17, 15, 51, 50, 33] is a seminal optimization problem that has
grown with today's rich and diverse optimization modeling and algorithmic landscape. LP is …