CIM-PPO: Proximal Policy Optimization with Liu-Correntropy Induced Metric.

Yunxiao Guo Han Long Xiaojun Duan Kaiyuan Feng Maochu Li Xiaying Ma

Published in: CoRR (2021)

Keyphrases

optimization algorithm
global optimization
data sets
distance measure
optimization method
database
neural network
reinforcement learning
distance function
evaluation metrics
e learning
simulated annealing
optimal policy
combinatorial optimization
metric learning
direct search