From 48b830eda6d4115100cf35ddcbbba4dfb42738b0 Mon Sep 17 00:00:00 2001 From: Tongzheng Ren Date: Mon, 6 Nov 2017 13:50:35 +0800 Subject: [PATCH] TODO: policy optimizer --- tianshou/optimizer/README.md | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 tianshou/optimizer/README.md diff --git a/tianshou/optimizer/README.md b/tianshou/optimizer/README.md new file mode 100644 index 0000000..1b39f0d --- /dev/null +++ b/tianshou/optimizer/README.md @@ -0,0 +1,11 @@ +# Optimizer for policy gradient methods +TODO: +vanilla +introduce a baseline +REINFORCE +TRPO +PPO +GAE +NAF +DPG +ACKTR \ No newline at end of file