Hugging FaceIntermediate
Hugging Face Deep Reinforcement Learning Course
A free, practical guide to deep RL. Train agents from Q-learning to Proximal Policy Optimization in PyTorch.
Duration40+ hours
PriceFree
FormatMixed
LevelIntermediate
What you'll learn
- Deep Q-Networks and value-based reinforcement learning
- Policy gradients and Proximal Policy Optimization (PPO)
- Multi-agent environments and self-play algorithms
- Evaluate and publish trained agents to the Hugging Face Hub
About this course
Thomas Simonini's free, hands-on curriculum from Hugging Face. You learn how agents interact with environments, write policy gradients, and train models on Gymnasium and Unity games. Complete the hands-on assignments and publish your trained agents to the Hub. Confirm the current syllabus on huggingface.co/learn/deep-rl-course. We are not affiliated with Hugging Face.
Prerequisites
Python and basic familiarity with PyTorch and neural networks.