Accelerating Primal-Dual Methods for Regularized Markov Decision Processes

DOI10.1137/21m1468851arXiv2202.10506MaRDI QIDQ6202767

Lexing Ying, Inderjit S. Dhillon, Haoya Li, Unnamed Author

Publication date: 27 February 2024

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

Full work available at URL: https://arxiv.org/abs/2202.10506

zbMATH Keywords

primal-dual methodMarkov decision processreinforcement learningentropy regularization

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) Lyapunov and storage functions (93D30) Markov and semi-Markov decision processes (90C40) Acceleration of convergence in numerical analysis (65B99)

Cites Work

• Unnamed Item
• Unnamed Item
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• A note on optimization formulations of Markov decision processes
• Policy mirror descent for reinforcement learning: linear convergence, new sampling complexity, and generalized problem classes
• 10.1162/jmlr.2003.3.4-5.803
• Randomized Linear Programming Solves the Markov Decision Problem in Nearly Linear (Sometimes Sublinear) Time
• Approximate Newton Policy Gradient Algorithms

This page was built for publication: Accelerating Primal-Dual Methods for Regularized Markov Decision Processes