CS_ALearn/deep-rl-class
1
0
Fork 0
mirror of https://github.com/huggingface/deep-rl-class.git synced 2026-04-05 03:28:05 +08:00
Code Issues Projects Releases Wiki Activity

docs: wrap eval_env in Monitor 📝

Browse Source
This commit is contained in:
Roberto Schiavone
2023-06-02 15:30:00 +02:00
parent 9802c0b6b4
commit 7eab5ef2ed
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
units/en/unit1/hands-on.mdx
View File

@@ -200,8 +200,9 @@ from huggingface_hub import (
) # To log to our Hugging Face account to be able to upload models to the Hub.
from stable_baselines3 import PPO
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.env_util import make_vec_env
from stable_baselines3.common.evaluation import evaluate_policy
from stable_baselines3.common.monitor import Monitor
```
## Understand Gymnasium and how it works 🤖
@@ -448,6 +449,7 @@ model.save(model_name)
## Evaluate the agent 📈
- Remember to wrap the environment in a [Monitor](https://stable-baselines3.readthedocs.io/en/master/common/monitor.html).
- Now that our Lunar Lander agent is trained 🚀, we need to **check its performance**.
- Stable-Baselines3 provides a method to do that: `evaluate_policy`.
- To fill that part you need to [check the documentation](https://stable-baselines3.readthedocs.io/en/master/guide/examples.html#basic-usage-training-saving-loading)
@@ -471,7 +473,7 @@ mean_reward, std_reward =
```python
# @title
eval_env = gym.make("LunarLander-v2")
eval_env = Monitor(gym.make("LunarLander-v2"))
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
```
@@ -589,7 +591,7 @@ repo_id = "ThomasSimonini/ppo-LunarLander-v2" # Change with your repo id, you c
commit_message = "Upload PPO LunarLander-v2 trained agent"
# Create the evaluation env and set the render_mode="rgb_array"
eval_env = DummyVecEnv([lambda: gym.make(env_id, render_mode="rgb_array")])
eval_env = DummyVecEnv([lambda: Monitor(gym.make(env_id, render_mode="rgb_array"))])
# PLACE the package_to_hub function you've just filled here
package_to_hub(
@@ -660,7 +662,7 @@ Let's evaluate this agent:
```python
# @title
eval_env = gym.make("LunarLander-v2")
eval_env = Monitor(gym.make("LunarLander-v2"))
mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)
print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
```