Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment.

Apan Dastider Mingjie Lin

Published in: CoRR (2022)

Keyphrases

non stationary
policy gradient
model free reinforcement learning
mobile robot
dynamic environments
random fields
autoregressive
multiresolution
neural network
signal processing
monte carlo
function approximation
optimal control
blind source separation