Online inverse reinforcement learning for nonlinear systems.

Ryan Self Michael Harlan Rushikesh Kamalapurkar

Published in: CoRR (2018)

Keyphrases

nonlinear systems
inverse reinforcement learning
adaptive control
fuzzy model
control law
fuzzy systems
learning rate
preference elicitation
adaptive neural control
fuzzy control
real time
fuzzy controller
reward function
data mining
neural network
sufficient conditions
state space
dynamic programming