From b4f89c9b7afd620f44691993a823bcb4b5a5d569 Mon Sep 17 00:00:00 2001 From: Dominik Roth Date: Sun, 2 Jun 2024 12:00:19 +0200 Subject: [PATCH] Added TODO fro module docs --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index f6e17a6..def62fb 100644 --- a/README.md +++ b/README.md @@ -33,6 +33,7 @@ Fancy RL provides two main components: For environments, you can pass any [gymnasium](https://gymnasium.farama.org/) or [Fancy Gym](https://alrhub.github.io/fancy_gym/) environment ID as a string, a function returning a gymnasium or torchrl environment, an already instantiated gymnasium or torchrl environment, or a dict that will be passed to gymnasium.make. Check 'example/example.py' for a more complete usage example. 2. **Additional Modules for TRPL**: Designed to integrate with torchrl's primitives-first approach, these modules are ideal for building custom algorithms with precise trust region projections. + Oh, you want documentation for these? To bad... (TODO) ## Background on Trust Region Policy Layers (TRPL)