Estimation of Reward Function Maximizing Learning Efficiency in Inverse Reinforcement Learning.

Yuki Kitazato Sachiyo Arai

Published in: ICAART (2) (2018)

Keyphrases

inverse reinforcement learning
reward function
preference elicitation
reinforcement learning
data mining
markov decision processes
partially observable
machine learning
bayesian networks
prior knowledge
state space
dynamical systems
learning tasks
learning agent