Courses/Reinforcement Learning

Reinforcement Learning

Policy gradient, Q-learning, and actor-critic methods built from the Bellman equation up. Train agents in MuJoCo and Atari.

Intermediate14 weeks · 14 lessons

Your progress0 / 14 · 0%

Lessons

Week 1: Reinforcement Learning Problem Formulation

Week 2: Multi-Armed Bandits

Week 3: Dynamic Programming for Finite MDPs

Week 4: Monte Carlo and Temporal-Difference Learning

Week 5: Function Approximation in Reinforcement Learning

Week 6: Deep Q-Learning and Variants

Week 7: Policy Gradient and Actor–Critic Methods

Week 8: Modern Deep Reinforcement Learning Algorithms

Week 9: Exploration, Partial Observability, and Multi-Agent Reinforcement Learning

Week 10: Model-Based Reinforcement Learning and Planning

Week 11: Offline Reinforcement Learning

Week 12: Reinforcement Learning from Human Feedback

Week 13: Direct Preference Optimization and GRPO

Week 14: Agentic Systems and Course Capstone