Efficient Reinforcement Learning Using State-Action Uncertainty with Multiple Heads.

Tomoharu Aizu Takeru Oba Norimichi Ukita

Published in: ICANN (8) (2023)

Keyphrases

supervised learning
reinforcement learning
state action
machine learning
learning algorithm
markov decision process
action space
temporal difference
state space
incomplete information
evaluation function
function approximation
function approximators
optimal control
state transitions
average reward
stochastic games