Online Learning of non-Markovian Reward Models.

Gavin Rens Jean-François Raskin Raphaël Reynouard Giuseppe Marra

Published in: ICAART (2) (2021)

Keyphrases

online learning
reinforcement learning
probabilistic model
computer mediated
learning algorithm
prior knowledge
stochastic process
data sets
distance education
statistical models
process model
learning experience
markov chain
feature space
multi agent
social networks
information retrieval
neural network