updated docs (#383)

docs/content/basic_usage.md

@@ -21,13 +21,5 @@ The environment being run can be selected with the `--env` option, eg:
 
 ## Training an Agent
 
-If you want to train an agent with reinforcement learning, I recommend using the code found in the [torch-rl](https://github.com/lcswillems/torch-rl) repository. 
-This code has been tested and is known to work with this environment. The default hyper-parameters are also known to converge.
-
-A sample training command is:
-
-```
-cd torch-rl
-python3 -m scripts.train --env MiniGrid-Empty-8x8-v0 --algo ppo
-```
+If you want to train an agent with reinforcement learning, please refer to the [training tutorial](training.md).
 

docs/content/training.md

@@ -4,7 +4,7 @@ title: Training Minigrid Environments
 firstpage:
 ---
 
-## Training Minigrid Environments
+# Training Minigrid Environments
 
 The environments in the Minigrid library can be trained easily using [StableBaselines3](https://stable-baselines3.readthedocs.io/en/master/). In this tutorial we show how a PPO agent can be trained on the `MiniGrid-Empty-16x16-v0` environment.