A Stochastic Composite Augmented Lagrangian Method for Reinforcement Learning.

Yongfeng Li Mingming Zhao Weijie Chen Zaiwen Wen

Published in: SIAM J. Optim. (2023)

Keyphrases

reinforcement learning
augmented lagrangian method
convex optimization
augmented lagrangian
total variation
total variation regularization
constrained minimization
machine learning
genetic algorithm
alternating direction
high resolution
denoising
optimal policy
cross validation
global convergence