CS_ALearn/deep-rl-class
1
0
Fork 0
mirror of https://github.com/huggingface/deep-rl-class.git synced 2026-04-03 10:38:27 +08:00
Code Issues Projects Releases Wiki Activity

Merge pull request #337 from robertoschiavone/main

Browse Source 
fix: wrap eval_env in Monitor 🐛
This commit is contained in:
Thomas Simonini
2023-06-02 15:55:31 +02:00
committed by GitHub
parent 2595a52462 7eab5ef2ed
commit 39eef811fd
2 changed files with 12 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
notebooks/unit1/unit1.ipynb
View File

@@ -338,8 +338,9 @@
"from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub.\n",
"\n",
"from stable_baselines3 import PPO\n",
"from stable_baselines3.common.env_util import make_vec_env\n",
"from stable_baselines3.common.evaluation import evaluate_policy\n",
"from stable_baselines3.common.env_util import make_vec_env"
"from stable_baselines3.common.monitor import Monitor"
]
},
{
@@ -738,6 +739,7 @@
},
"source": [
"## Evaluate the agent 📈\n",
"- Remember to wrap the environment in a [Monitor](https://stable-baselines3.readthedocs.io/en/master/common/monitor.html).\n",
"- Now that our Lunar Lander agent is trained 🚀, we need to **check its performance**.\n",
"- Stable-Baselines3 provides a method to do that: `evaluate_policy`.\n",
"- 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)\n",
@@ -784,7 +786,7 @@
"outputs": [],
"source": [
"#@title\n",
"eval_env = gym.make(\"LunarLander-v2\")\n",
"eval_env = Monitor(gym.make(\"LunarLander-v2\"))\n",
"mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)\n",
"print(f\"mean_reward={mean_reward:.2f} +/- {std_reward}\")"
]
@@ -917,7 +919,7 @@
"env_id = \n",
"\n",
"# Create the evaluation env and set the render_mode=\"rgb_array\"\n",
"eval_env = DummyVecEnv([lambda: gym.make(env_id, render_mode=\"rgb_array\")])\n",
"eval_env = DummyVecEnv([lambda: Monitor(gym.make(env_id, render_mode=\"rgb_array\"))])\n",
"\n",
"\n",
"# TODO: Define the model architecture we used\n",
@@ -1096,7 +1098,7 @@
"cell_type": "code",
"source": [
"#@title\n",
"eval_env = gym.make(\"LunarLander-v2\")\n",
"eval_env = Monitor(gym.make(\"LunarLander-v2\"))\n",
"mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)\n",
"print(f\"mean_reward={mean_reward:.2f} +/- {std_reward}\")"
],

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}")
```