Context-Based Soft Actor Critic for Environments with Non-stationary Dynamics.

Yuan Pu Shaochen Wang Xin Yao Bin Li

Published in: CoRR (2021)

Keyphrases

non stationary
actor critic
temporal evolution
reinforcement learning
dynamical systems
optimal control
policy gradient
temporal difference
autoregressive
dynamic environments
random fields
empirical mode decomposition
gradient method
policy iteration
function approximation
neuro fuzzy
change point detection