A Stochastic Composite Augmented Lagrangian Method for Reinforcement Learning

DOI10.1137/21m1421726zbMath1519.90109arXiv2105.09716OpenAlexW3160601834MaRDI QIDQ6161305

ZaiWen Wen, Yongfeng Li, Wei-Jie Chen, Mingming Zhao

Publication date: 27 June 2023

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.09716

zbMATH Keywords

linear programmingaugmented Lagrangian methodoff-policy learningdeep reinforcement learning

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Linear programming (90C05) Stochastic programming (90C15) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
• Some continuity properties of polyhedral multifunctions
• Monotone Operators and the Proximal Point Algorithm
• Randomized Linear Programming Solves the Markov Decision Problem in Nearly Linear (Sometimes Sublinear) Time
• Convex analysis and monotone operator theory in Hilbert spaces