Back to Catalog
Reinforcement Learning: Agents
The closest thing to true AGI. Teach AI to learn by trial and error. From Q-Learning to PPO, build agents that play games and trade stocks.
12 Weeks Expert
What you'll build
Understand Markov Decision Processes
Implement Q-Learning from scratch
Master Deep Q-Network (DQN)
Train PPO Agents (Proximal Policy Optimization)
Build Gym Environments
Your Progress
Track your journey through this course.
0% Completed0/8 Modules
Your progress is stored locally on this device. Export it to continue on another device.
Curriculum
Frequently Asked Questions
Is this useful?
Yes. Used in Robotics, Trading, and optimizing Data Center cooling.
Math?
Heavy. Bellman Equation and Policy Gradients.