Skip to main content

Reinforcement Learning

Q-learning, policy gradients, deep RL, and AI agents.

Course Duration: 12 hours​

What You'll Learn​

  • RL fundamentals
  • Markov Decision Processes
  • Q-Learning
  • Policy gradients
  • Deep RL algorithms
  • Building AI agents

Prerequisites​

  • Deep Learning knowledge
  • Python and PyTorch

Course Modules​

  1. Introduction to RL
  2. Markov Decision Processes
  3. Bellman Equations
  4. Dynamic Programming
  5. Monte Carlo Methods
  6. Temporal Difference Learning
  7. Q-Learning
  8. Deep Q-Networks (DQN)
  9. Policy Gradient Methods
  10. Actor-Critic
  11. PPO and SAC
  12. Project: Game-Playing Agent

Algorithms Covered​

  • Q-Learning
  • DQN
  • REINFORCE
  • A2C / A3C
  • PPO
  • SAC