Sign in
Combination of learning from non-optimal demonstrations and feedbacks using inverse reinforcement learning and Bayesian policy improvement.
Ali Ezzeddine
Nafee Mourad
Babak Nadjar Araabi
Majid Nili Ahmadabadi
Published in:
Expert Syst. Appl. (2018)
Keyphrases
</>
inverse reinforcement learning
partially observable environments
bayesian nonparametric
learning algorithm
reinforcement learning
reward function
control policy
preference elicitation
machine learning
decision making
bayesian networks
decision theoretic