Asynchronous Advantage Actor Critic: Non-asymptotic Analysis and Linear Speedup.

Han Shen Kaiqing Zhang Mingyi Hong Tianyi Chen

Published in: CoRR (2020)

Keyphrases

asymptotic analysis
actor critic
fluid model
lyapunov stability
reinforcement learning
recursive least squares
policy gradient
gradient method
reinforcement learning algorithms
stochastic model
neural network
evolutionary algorithm
state space
optimal control
approximate dynamic programming