Trust-Region Inverse Reinforcement Learning.

Kun Cao Lihua Xie

Published in: IEEE Trans. Autom. Control. (2024)

Keyphrases

inverse reinforcement learning
trust region
global optimum
preference elicitation
column generation
optimization methods
reward function
log likelihood
newton method
hessian matrix
levenberg marquardt
line search
mean shift
lower bound
simulated annealing
cost function
maximum likelihood
fuzzy logic