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

Update hands-on.mdx

Browse Source
This commit is contained in:
Thomas Simonini
2023-01-04 14:10:57 +01:00
committed by GitHub
parent 49692e07b7
commit 89e97f0196
1 changed files with 5 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
units/en/unit4/hands-on.mdx
View File

@@ -67,6 +67,7 @@ To test its robustness, we're going to train it in 2 different simple environmen
We're constantly trying to improve our tutorials, so **if you find some issues in this notebook**, please [open an issue on the GitHub Repo](https://github.com/huggingface/deep-rl-class/issues).
## Objectives of this notebook 🏆
At the end of the notebook, you will:
- Be able to **code from scratch a Reinforce algorithm using PyTorch.**
@@ -74,23 +75,13 @@ At the end of the notebook, you will:
- Be able to **push your trained agent to the Hub** with a nice video replay and an evaluation score 🔥.
## Prerequisites 🏗️
Before diving into the notebook, you need to:
🔲 📚 [Study Policy Gradients by reading Unit 4](https://huggingface.co/deep-rl-course/unit4/introduction)
# Let's code Reinforce algorithm from scratch 🔥
To validate this hands-on for the certification process, you need to push your trained models to the Hub.
- Get a result of >= 350 for `Cartpole-v1`.
- Get a result of >= 5 for `PixelCopter`.
To find your result, go to the leaderboard and find your model, **the result = mean_reward - std of reward**. **If you don't see your model on the leaderboard, go at the bottom of the leaderboard page and click on the refresh button**.
For more information about the certification process, check this section 👉 https://huggingface.co/deep-rl-course/en/unit0/introduction#certification-process
## An advice 💡
It's better to run this colab in a copy on your Google Drive, so that **if it timeouts** you still have the saved notebook on your Google Drive and do not need to fill everything from scratch.
@@ -209,7 +200,8 @@ As explained in [Reinforcement Learning Tips and Tricks](https://stable-baseline
> Validate the implementation by making it run on harder and harder envs (you can compare results against the RL zoo). You usually need to run hyperparameter optimization for that step.
___
### The CartPole-v1 environment
> A pole is attached by an un-actuated joint to a cart, which moves along a frictionless track. The pendulum is placed upright on the cart and the goal is to balance the pole by applying forces in the left and right direction on the cart.
@@ -788,8 +780,6 @@ def push_to_hub(repo_id, model, hyperparameters, eval_env, video_fps=30, local_r
print(f"Your model is pushed to the hub. You can view your model here: {repo_url}")
```
### .
By using `push_to_hub` **you evaluate, record a replay, generate a model card of your agent and push it to the Hub**.
This way:
@@ -982,6 +972,7 @@ push_to_hub(
```
## Some additional challenges 🏆
The best way to learn **is to try things on your own**! As you saw, the current agent is not doing great. As a first suggestion, you can train for more steps. But also trying to find better parameters.
In the [Leaderboard](https://huggingface.co/spaces/huggingface-projects/Deep-Reinforcement-Learning-Leaderboard) you will find your agents. Can you get to the top?