diff --git a/README.md b/README.md
index 8e20693..462b097 100644
--- a/README.md
+++ b/README.md
@@ -30,7 +30,7 @@ Fancy RL provides two main components:
    ppo.train()
    ```
 
-   For environments, you can pass any gymnasium environment ID as a string, a function returning a gymnasium environment, or an already instantiated gymnasium environment. Future plans include supporting other torchrl environments.
+   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 environment, or an already instantiated gymnasium environment. Future plans include supporting other torchrl environments.
    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.
diff --git a/fancy_rl/on_policy.py b/fancy_rl/on_policy.py
index eeb22ac..6093e29 100644
--- a/fancy_rl/on_policy.py
+++ b/fancy_rl/on_policy.py
@@ -9,6 +9,10 @@ from torchrl.envs import ExplorationType, set_exploration_type
 from torchrl.envs.libs.gym import GymWrapper
 from torchrl.record import VideoRecorder
 import gymnasium as gym
+try:
+    import fancy_gym
+except ImportError:
+    pass
 
 class OnPolicy(ABC):
     def __init__(