AI Fundamentals Course Practice: A Complete Learning Path from Vacuum Cleaner Agents to Reinforcement Learning

The AI-Fundamentals-Coursework course, open-sourced by emilloof on GitHub, provides AI beginners with a complete practice path from reactive agents to state space search and then to reinforcement learning. It implements core algorithms using Python and Java, helping learners integrate theory with hands-on practice.

This course is designed for people who want to deeply understand basic AI concepts, including computer science undergraduates, AI self-learners, interview preparers, and career-changer developers. It addresses the disconnect between theory and practice, allowing learners to master core concepts through hands-on implementation.

The course is divided into three experimental modules:

1. Intelligent Agents and Environment Interaction (Python)：Implement random agents, reactive agents, and custom state-tracking agents in the vacuum cleaner world, understanding the differences between agent types;
2. State Space Search and Path Planning (Java)：Implement BFS, DFS, and graph search algorithms, mastering the core of path planning;
3. Introduction to Reinforcement Learning (Java/Eclipse)：Implement Q-Learning, understanding the balance between exploration and exploitation, and value function estimation.

Course features include:

• Gradual difficulty progression: From simple agents to complex reinforcement learning, gradually increasing in difficulty;
• Multi-language practice: Combination of Python (concise and fast) and Java (strongly typed/OOP), experiencing different paradigms;
• Bridge between theory and code: Corresponding to core concepts in Russell & Norvig's Artificial Intelligence: A Modern Approach (PEAS, search problem formalization, MDP, etc.), transforming abstract theory into runnable code.

Technical environment requirements: Python3.8+, JDK, Eclipse IDE (recommended). Getting started steps:

• Experiment 1: Enter the TDDC17_lab1_python directory and run python run_lab1.py;
• Experiment 2: Use compile.sh and run.sh scripts to compile and run;
• Experiment3: Import the rl_workspace directory in Eclipse and run using the pre-configured Launch file.

The course provides expansion opportunities:

• Experiment1: Implement goal-based or utility-based agents;
• Experiment2: Try A* search, iterative deepening search, and other algorithms;
• Experiment3: Explore advanced reinforcement learning methods such as SARSA, DQN, etc.

The AI-Fundamentals-Coursework course covers core AI practices from basics to advanced levels through a complete teaching design. It emphasizes the importance of hands-on implementation of classic algorithms, providing learners with a proven AI practice path to help them truly understand AI rather than just use it.