Guarded Policy Optimization with Imperfect Online Demonstrations.

Zhenghai Xue Zhenghao Peng Quanyi Li Zhihan Liu Bolei Zhou

Published in: ICLR (2023)

Keyphrases

optimization algorithm
online learning
global optimization
real time
discrete optimization
constrained optimization
optimal policy
optimization problems
neural network
optimization methods
databases
least squares
cost function
particle swarm optimization
information systems
machine learning
database