Students will understand the fundamental concepts and key algorithms of reinforcement learning (DP, MC, TD, Q-learning), and acquire knowledge of advanced methods such as DQN, Policy Gradient, and Actor–Critic. The course integrates lectures with hands-on practice, enabling students to implement and validate algorithms. Through this, they will develop foundational competencies to apply reinforcement learning to problem-solving in mechanical engineering and robotics.

Week 1 Course overview & Deep Learning Review I - Basic Concepts, Perceptron, Activation, Loss
Week 2 Deep Learning Review II – Deep Learning, Backpropagation
Week 3 Deep Learning Review Ⅲ – Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN)
Week 4 Markov Property, Markov Process, Markov Reward Process, Markov Decision Process
Week 5 Policy Iteration
Week 6 Value Iteration, MC Prediction, TD Prediction
Week 7 TD-λ Prediction, MC Control
Week 8 SARSA, SARS-λ, Q-Learning
Week 9 Function Approximation, Deep Q-Network (DQN)
Week 10 Midterm Exam / REINFORCE
Week 11 No Class (National Holiday, University Festival)
Week 12 Actor–Critic Methods
Week 13 PPO
Week 14 SAC
Week 15 Project preparation
Week 16 Report Submission, and Course Wrap-up

The course will be delivered through lectures combined with hands-on practice.