AI Academy
Hugging Face·Hugging Face

Deep Reinforcement Learning Course

From Q-learning to PPO — train agents on Unity ML, Godot and classic gym environments.

Self-paced·Advanced·English·Free· Certificate·~40h total
Skills you'll learn
  • Reinforcement Learning
  • PyTorch
Prerequisites
  • Python
  • Deep Learning
Learning outcomes
  • Train PPO agents
  • Understand policy gradients
Deep LearningRoboticsAI Research
Part of these learning paths
Become an AI Researcher
Provider
Hugging Face

Free NLP, Deep RL, Agents & Diffusion courses.

Official site