Advanced Certificate

Reinforcement Learning A-Z

Master reinforcement learning from fundamentals to cutting-edge algorithms. Build AI agents that learn to play games, control robots, and make optimal decisions in complex environments.

4.8(987 reviews)
6,234 students45 hoursUpdated February 2026

Dr. Alex Kumar

RL Research Lead at 1.ML

Free

Full access to all content

Duration45 hours
Lessons130
LevelAdvanced
LanguageEnglish
CertificateIncluded

What You'll Learn

Markov Decision Processes
Q-Learning and SARSA
Deep Q-Networks (DQN)
Policy gradient methods
Actor-Critic algorithms
Multi-agent reinforcement learning

Requirements

  • Strong Python skills
  • Deep learning experience
  • Probability and statistics
  • Linear algebra

Course Curriculum

Introduction to RLFREE
1:00:00
Markov Decision ProcessesFREE
1:30:00
Dynamic Programming
1:45:00
Monte Carlo Methods
1:30:00

Instructor

Dr. Alex Kumar

RL Research Lead at 1.ML

Dr. Alex Kumar leads RL research at 1.ML. With publications at ICML and NeurIPS, he's at the forefront of RL research. His work on multi-agent RL has been used in production systems at major tech companies.