加簽表單：https://docs.google.com/forms/d/e/1FAIpQLSfzGZsk6-7aVWkBP2DBYVnTAIGrCzvo4l6hMmjesjjL4c62kA/viewform?usp=sf_link

Reinforcement learning (RL) is a subfield of machine learning concerned with developing algorithms that can learn to make decisions by interacting with the environment. This course will cover the fundamentals of reinforcement learning. We will also explore more advanced topics, such as deep reinforcement learning (deep RL) algorithms, imitation learning, hierarchical RL, meta-RL, programmatic RL, etc.

Throughout the course, students will implement and experiment with various RL algorithms, including Q-learning, policy gradient, and actor-critic methods. We will use popular RL frameworks, such as OpenAI Gym, to build and train RL models for a range of applications, such as games, robotics, and recommendation systems.

By the end of the course, students will have a solid understanding of the core concepts of reinforcement learning and the ability to apply these concepts to real-world problems. They will also be familiar with current research trends in RL and have the skills to continue learning and experimenting with RL algorithms beyond the scope of the course.