Imitation learning based on entropy-regularized forward and inverse reinforcement learning.

Eiji Uchibe Kenji Doya

Published in: CoRR (2020)

Keyphrases

imitation learning
inverse reinforcement learning
reinforcement learning
preference elicitation
reward function
robotic systems
humanoid robot
maximum margin
temporal difference
learning algorithm
hidden markov models
state space
higher order
graphical models
function approximation