TODO: policy optimizer

This commit is contained in:
Tongzheng Ren 2017-11-06 13:50:35 +08:00
parent 6a4adac1a0
commit 48b830eda6

View File

@ -0,0 +1,11 @@
# Optimizer for policy gradient methods
TODO:
vanilla
introduce a baseline
REINFORCE
TRPO
PPO
GAE
NAF
DPG
ACKTR