CCPO: Conservatively Constrained Policy Optimization Using State Augmentation.

Zepeng Wang Xiaochuan Shi Chao Ma Libing Wu Jia Wu

Published in: ECAI (2023)

Keyphrases

global optimization
optimization method
concave convex procedure
constrained optimization
machine learning
genetic algorithm
information systems
state space
combinatorial optimization
state variables
discrete optimization
optimization strategies
saddle point