Guarded Policy Optimization with Imperfect Online Demonstrations.

Zhenghai Xue Zhenghao Peng Quanyi Li Zhihan Liu Bolei Zhou

Published in: CoRR (2023)

Keyphrases

online learning
optimization algorithm
real time
global optimization
optimization problems
constraint satisfaction problems
optimization model
databases
search algorithm
e government
optimization methods
probabilistic databases
stochastic gradient