Welcome to the "Course on Reinforcement Learning," a practical educational resource designed to introduce you to the world of reinforcement learning (RL). This course will guide you through the foundational concepts and advanced strategies of RL, using hands-on examples and interactive tasks.
You will start with an introduction to the basic principles of RL and progress through to implementing advanced algorithms like Deep Q-Networks (DQN).
- Foundations of Reinforcement Learning: Grasp the basic concepts, terminologies, and problem-solving approaches in RL.
- Environment and Agent Design: Understand how to model problems using the RL framework and design agents to interact with environments.
- Q-Learning with CartPole: Implement Q-learning to solve the CartPole balancing problem, a classic example in RL.
- Deep Q-Network Task: Dive into Deep Q-Networks (DQN) and learn how to apply deep learning to reinforcement learning.
- Advanced Strategies and Optimizations: Explore advanced RL strategies and learn optimization techniques for better performance.
- Git
- Python
- A WandB account to be able to watch the learning of weights and biases during training (optional).
This course was created by Even Klemsdal, one of the founding member of Cogito NTNU, and one of our most skilled members.
 Even Klemsdal |