deep-rl-class
deep-rl-class copied to clipboard
huggingface
This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.
After cloning the Unity ml-agents package, I tried to install the experimental version of the library that allows you to push your trained agent to the Hub by executing the...
Hi In the text of **The advantages and disadvantages of policy-gradient methods** , you wanted to write `policy-based methods` but as a typo, you wrote `value-based methods` : > Advantages...
I have been checking FinRL package. This is basically an open-source framework meant for trading of various financial instruments (stocks, crypto, portfolio allocation .. etc). - https://github.com/AI4Finance-Foundation/FinRL/tree/master For reinforcement learning...
need to add !pip install gymnasium==0.29.1 pickle5 from stable_baselines3 import PPO before loading the model from hugging face : from huggingface_sb3 import load_from_hub from stable_baselines3 import PPO repo_id = "ToonAga/ppo-LunarLander-v2"...
Hi, I'm facing a _KeyError: 'email'_ error when running the following command, i.e., pushing to the hub on the Colab for Unit 3. I'm not so sure what triggered it,...
When you define stochastic policies, you write:  \pi (a|s) = P [A|s] LHS is a specific real number in [0,1] while on the RHS you have a probability distribution,...
To fix error with dependencies which I got from Colab, I think `sample-factory` could be safely updated to `2.1.1` Error which I get: ``` Collecting sample-factory==2.0.2 Downloading sample_factory-2.0.2-py3-none-any.whl.metadata (11 kB)...
Metadata
Owner
Metadata
This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.