Back

Reinforcement learning is the discipline behind game-playing AI, robotics, and increasingly LLM alignment. This course covers RL fundamentals through modern approaches like PPO and GRPO, culminating in a trained game-solving agent.

✅ What’s Inside:

  1. The RL Problem Framework
  2. Markov Decision Processes
  3. Q-Learning from Scratch
  4. Deep Q-Networks (DQN)
  5. Policy Gradient Methods
  6. Proximal Policy Optimization (PPO)
  7. Actor-Critic Architectures
  8. Reward Shaping
  9. Environment Design
  10. Multi-Agent RL Intro
  11. RLHF in Language Models
  12. Project: Train a Game-Solving Agent