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

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

Published in: NeurIPS (2021)

Keyphrases

reinforcement learning
user feedback
state space
theoretical basis
real time
neural network
real world
decision making
function approximation
learning process
computational model
theoretical framework
markov decision processes