We adapt recent tools developed for the analysis of Stochastic Gradient Descent (SGD) in
non-convex optimization to obtain convergence and sample complexity guarantees for the …

Modern policy optimization methods in reinforcement learning, such as TRPO and PPO, owe
their success to the use of parameterized policies. However, while theoretical guarantees …

Actor-critic (AC) algorithms have been widely used in decentralized multi-agent systems to
learn the optimal joint control policy. However, existing decentralized AC algorithms either …

Bilevel optimization has been recently used in many machine learning problems such as
hyperparameter optimization, policy optimization, and meta learning. Although many bilevel …

Proximal policy optimization (PPO) is a recent advancement in reinforcement learning,
which is formulated as an unconstrained optimization problem including two terms …

Structural model pruning is a prominent approach used for reducing the computational cost
of Convolutional Neural Networks (CNNs) before their deployment on resource-constrained …

Improving sample efficiency has been a longstanding goal in reinforcement learning. This
paper proposes VRMPO algorithm: a sample efficient policy gradient method with stochastic …

We study the convergence of several natural policy gradient (NPG) methods in infinite-
horizon discounted Markov decision processes with regular policy parametrizations. For a …

This paper revisits the convergence of Stochastic Mirror Descent (SMD) in the contemporary
nonconvex optimization setting. Existing results for batch-free nonconvex SMD restrict the …

Markov Decision Processes (MDPs) are a formal framework for modeling and solving
sequential decision-making problems. In finite-time horizons such problems are relevant for …