A Small Gain Analysis of Single Timescale Actor Critic

DOI10.1137/22m1483335arXiv2203.02591OpenAlexW4367311942MaRDI QIDQ6042800

Bahman Gharesifard, Alexander Olshevsky

Publication date: 4 May 2023

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

Full work available at URL: https://arxiv.org/abs/2203.02591

zbMATH Keywords

nonconvex optimizationreinforcement learningactor critic

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Artificial intelligence (68Txx)

Related Items

On the sample complexity of actor-critic method for reinforcement learning with function approximation

Cites Work

• Unnamed Item
• Unnamed Item
• Policy gradient in Lipschitz Markov decision processes
• Fundamental design principles for reinforcement learning algorithms
• Introduction to Nonlinear Optimization
• An analysis of temporal-difference learning with function approximation
• OnActor-Critic Algorithms
• Taylor series expansions for stationary Markov chains
• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes
• Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies
• Deep Reinforcement Learning: A State-of-the-Art Walkthrough
• Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
• A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic