Within the scope of prediction: Shaping intrinsic rewards via evaluating uncertainty.

Xiaoshu Zhou Fei Zhu Peiyao Zhao

Published in: Expert Syst. Appl. (2022)

Keyphrases

prediction accuracy
reinforcement learning
prediction error
prediction algorithm
markov decision processes
prediction model
prediction intervals
data sets
incomplete information
reward shaping
information systems
website
multi agent
regression model
bandit problems