On the Theory of Reinforcement Learning with Once-per-Episode Feedback.

Niladri S. Chatterji Aldo Pacchiano Peter L. Bartlett Michael I. Jordan

Published in: CoRR (2021)

Keyphrases

reinforcement learning
theoretical basis
general theory
computational model
model free
optimal control
theoretical framework
machine learning
learning process
multi agent
neural network
optimal policy
learning environment
function approximation
case study
decision theory
learning algorithm