deep-rl-class
deep-rl-class copied to clipboard
huggingface
This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.
Just to report that huggingface-projects/AIvsAI-SoccerTwos is not working. I'm using this link : https://huggingface.co/spaces/huggingface-projects/AIvsAI-SoccerTwos
I used Google Colab on Win10. If I do not specify my account name in the repo-id, it's like the pipeline is trying to push the model on Thomas repo:...
This update solves or merge: - #438 - #436 - #434 - [X] #437 - #435 - #420 - #432 - [X] #458 - [X] #455 - #456 - #453...
Hi ! To ensure future students won't be to confused by the leaderboard of Taxi v3, I have added in the unit2 notebook the best possible score when respecting the...
# Describe the bug For Unit2 hands-on, in the evaluate_agent function, the `env.reset()` is in the for episode loop which means that, for the FrozenLake-v1 environment, **without** slippery, the initial...
# Describe the bug The model trains normally, but the package_to_hub process stuck with the following message: ℹ This function will save, evaluate, generate a video of your agent, create...
This PR proposes some changes to the description of the observation space. However, please verify the validity first since I'm not very familiar with this env. My current understanding after...
- I added (and commented) the following formula for epsilon calculation which as opposed to the current formula is dependent on the "n_training_episodes" (the two formulas output for some "n_training_episodes"...
Hi, - In unit2, in function "push_to_hub", the variable "env_id" has been used for the definition of variable "model_card". This variable, "env_id", hasn't been defined in the function "push_to_hub", and...
Metadata
Owner
Metadata
This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.