In this second part of Unit 8, we’ll get deeper into PPO optimization by using Sample-Factory, an asynchronous implementation of the PPO algorithm, to train our agent to play vizdoom (an open source version of Doom).
In the notebook, you’ll train your agent to play the Health Gathering level, where the agent must collect health packs to avoid dying. After that, you can train your agent to play more complex levels, such as Deathmatch.
Sound exciting? Let’s get started! 🚀
The hands-on is made by Edward Beeching, a Machine Learning Research Scientist at Hugging Face. He worked on Godot Reinforcement Learning Agents, an open-source interface for developing environments and agents in the Godot Game Engine.