deep-rl-class
deep-rl-class copied to clipboard
huggingface
This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.
# Describe the bug I can solve the one problem in this issue list. ``` # Go inside the repository and install the package %cd ml-agents !pip3 install -e ./ml-agents-envs...
Hello , I find something to improve ,in the unity section it have used multiagent which explained later in course ,I think it will be more useful to explain multiagent...
# Update: There is no need to install pickle, as it's already within Python 3.11. ```python # Colab python version !pyhon --version ``` ```python Python 3.11.11 ``` 1. Remove **pickle5**...
On the hands on section of unit 4 (policy gradient), when building the REINFORCE policy, the exercise has an intentional bug causing the error message `ValueError: The value argument to...
If you want to see what this reward function looks like mathematically, check [Puppo the Corgi presentation](https://blog.unity.com/technology/puppo-the-corgi-cuteness-overload-with-the-unity-ml-agents-toolkit). I can't see the above page, could you please update it?
The explanation of the given example `dqn.yml` file in **Unit3** _Train our Deep Q-Learning Agent to Play Space Invaders_ Section has a typo in the 3rd item. In line 6...
The link to "Puppo The Corgi" isn't working, and when we click on it it shows Not Found. https://colab.research.google.com/github/huggingface/deep-rl-class/blob/master/notebooks/bonus-unit1/bonus-unit1.ipynb#scrollTo=x7oR6R-ZIbeS
# Describe the bug I running [Unit3.jupyter](https://colab.research.google.com/github/huggingface/deep-rl-class/blob/main/notebooks/unit3/unit3.ipynb) in colab, and could not using GPU when I train model using this cell code ```python !python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4...
I have attempted the Lunar Lander several times and tried to check if it was accepted on the leaderboard for certification later on. I am having this run time error...
# Describe the bug I am running miniconda on my machine. The model trained fine and I entered the hugging-face token as well. However, when I tried to push to...
Metadata
Owner
Metadata
This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.