Reinforcement Learning
This course introduces the foundations and modern developments of Reinforcement Learning (RL), a machine learning approach where agents learn by interacting with their environment.
📊︎
Advanced
⏱
54 hours
🏅︎
Record of Achievement
🎁︎
For free
©
CC BY-SA 4.0
🌐︎
English
Overview
Reinforcement Learning (RL) enables agents to learn through trial and error, resulting in breakthroughs in games and robotics. This course introduces the mathematical foundations of RL and traces its development. Students will study key ideas like MDPs, value methods, policy search, model-based, and deep RL. Exercises include implementing algorithms, tuning hyperparameters, and evaluating agents. At the end of the course, you will apply your new skills to an interesting RL project of your choice.
Which topics will be covered?
- Mathematical foundations of reinforcement learning (e.g., Markov Decision Processes)
- Implementation of RL algorithms (e.g., Q-learning, Policy Gradient)
- Deep reinforcement learning with neural networks
- Design and evaluation of agents in simulated environments
What will I achieve?
On completion of the course you will be able to:
- Understand and explain core reinforcement learning concepts and algorithms
- Implement and tune RL agents in simulated environments
- Analyze and justify the theoretical foundations behind RL approaches
- Apply RL methods to design, train, and evaluate agents for a selected project
Which prerequisites do I need to fulfill?
- Python
- Deep Learning
- Foundations in AI and Machine Learning
