Fancy RL is a minimalistic and efficient implementation of Proximal Policy Optimization (PPO) and Trust Region Policy Layers (TRPL) using primitives from [torchrl](https://pypi.org/project/torchrl/). Future plans include implementing Soft Actor-Critic (SAC). This library focuses on providing clean and understandable code while leveraging the powerful functionalities of torchrl.
We provide optional integration with wandb.
diff --git a/fancy_rl.svg b/fancy_rl.svg
new file mode 100644
index 0000000..751041c
--- /dev/null
+++ b/fancy_rl.svg
@@ -0,0 +1,139 @@
+
+
+
+