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

Dohyeong Kim Songhwai Oh

Published in: CoRR (2023)

Keyphrases

trust region
reinforcement learning
global optimum
column generation
optimization methods
newton method
function approximation
levenberg marquardt
hessian matrix
state space
line search
learning algorithm
log likelihood
machine learning
least squares
linear program
branch and bound
neural network
objective function