From 1bef92bc6fdc4ac83fc53f4df1795f41d91f2b2b Mon Sep 17 00:00:00 2001 From: Thomas Simonini Date: Thu, 21 Apr 2022 15:24:29 +0200 Subject: [PATCH] Update README.md --- README.md | 72 +++++++++++++++++++++++++++++++++---------------------- 1 file changed, 43 insertions(+), 29 deletions(-) diff --git a/README.md b/README.md index 7deb5e6..9378d5b 100644 --- a/README.md +++ b/README.md @@ -1,54 +1,68 @@ -# The Hugging Face Deep Reinforcement Learning Bootcamp 🤗 +# The Hugging Face Deep Reinforcement Learning Class 🤗 -In this free bootcamp, you will: +In this free course, you will: - 📖 Study Deep Reinforcement Learning in **theory and practice**. - 🧑‍💻 Learn to **use famous Deep RL libraries** such as Stable Baselines3, RL Baselines3 Zoo, and RLlib. - 🤖 Train agents in **unique environments** such as SnowballFight, Huggy the Doggo 🐶, and classical ones such as Space Invaders and PyBullet. -- 💾 **Publish your trained agents in one line of code to the Hub**. But also **download powerful agents from the community**. +- 💾 **Publish your trained agents in one line of code to the Hugging Face Hub**. But also **download powerful agents from the community**. +- 🏆 **Participate in challenges** where you going to evaluate your agents against other teams. ➡️➡️➡️ Don't forget to sign up here: https://forms.gle/4bbgzs3oVZMjgDed7 The best way to keep in touch is to **join our discord server to exchange with the community and with us** 👉🏻 https://discord.gg/aYka4Yhff9 -And don't forget to share with your friends who want to learn 🤗 ! +And don't forget to share with your friends who want to learn 🤗! -## The Syllabus +## The Syllabus 🏗️ -# Unit 1: An Introduction to Deep Reinforcement Learning - - Theory: An Introduction to Deep Reinforcement Learning - - Hands-on: Train your first agent with SB3 - -# Bonus: Train Huggy the Doggo - -# Unit 2: Q-Learning - -# Unit 3: Deep Q-Learning and improvements +| May, the 4th | An Introduction to Deep Reinforcement Learning | Train a Deep Reinforcement Learning lander agent to land correctly on the Moon 🌕 using Stable-Baselines3 | +|---------------|----------------------------------------------------------|----------------------------------------------------------------------------------------------------------| +| May, the 11th | Bonus | Train Huggy the Doggo to catch the stick | +| May, the 18th | Q-Learning | Train an agent to cross a Frozen lake in this new version of the environment. | +| June, the 1st | Deep Q-Learning and improvements | Train a Deep Q-Learning agent to play Space Invaders | +| | Policy based methods | 🏗️ | +| | Actor Critic Methods | 🏗️ | +| | Proximal Policy Optimization (PPO) | 🏗️ | +| | Decision Transformers and offline Reinforcement Learning | 🏗️ | +| | Towards better explorations methods | 🏗️ | -# Unit 4: Policy based methods +## The library you'll learn during this course +- [Stable-Baselines3](https://github.com/DLR-RM/stable-baselines3) +- [RL Baselines3 Zoo](https://github.com/DLR-RM/rl-baselines3-zoo) +- [RLlib](https://docs.ray.io/en/latest/rllib/index.html) +- [CleanRL](https://github.com/vwxyzjn/cleanrl) +- More to come 🏗️ + +## The Environments you'll use +### Custom environments made by Hugging Face Team using Unity and Godot +- Huggy the Doggo 🐶 +(Huggy the Doggo is based on [Unity's Puppo the Corgi work](https://blog.unity.com/technology/puppo-the-corgi-cuteness-overload-with-the-unity-ml-agents-toolkit)) -# Unit 5: Actor Critic Methods + +- SnowballFight ☃️ +[snowballfight.gif](./assets/img/snowballfight.gif) +👉 Play it here : https://huggingface.co/spaces/ThomasSimonini/SnowballFight -# Unit 6: Proximal Policy Optimization (PPO) +- More to come -# Unit 7: Decision Transformers +# Gym classic controls environments +- Lunar-Lander v2: -- Introduction to Deep Reinforcement Learning - - Theory: C1 DRLC Introduction to Deep RL - - Practice: Lunar Lander - - Library: SB3 - - Bonus: Huggy -- Value based methods: Q-Learning - - Theory: Q-Learning - - Practice: Frozen lake updated version +# PyBullet + + +# Gym Atari environments + + +# MLAgents environments + + -- Deep Q-Learning and improvements - - Theory: Deep Q-Learning and DDQN - - Practice: