diff --git a/README.md b/README.md index 2bb0284..99bb013 100644 --- a/README.md +++ b/README.md @@ -1 +1,22 @@ # Torchy-Baselines + +TODO: +- SAC +- save/load +- automatic choice for action distribution +- predict +- better rescale (min + action * range) +- documentation +- flexible mlp +- logger +- better monitor wrapper? + +Later: +- get_parameters / set_parameters +- CNN policies + normalization +- tensorboard support +- DQN +- TRPO +- A2C +- ACER +- HER -> use stable-baselines because does not depends on tf?