TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning.

Dohyeong Kim Songhwai Oh

Published in: IEEE Robotics Autom. Lett. (2022)

Keyphrases

trust region
reinforcement learning
global optimum
column generation
optimization methods
hessian matrix
function approximation
log likelihood
newton method
state space
line search
levenberg marquardt
machine learning
optimization method
neural network
learning algorithm
scoring function