Course Overview
TOPThe AI+ Game Design Agent™ course explores how AI agents transform gameplay, decision-making, and player interaction in modern game design. It covers key topics such as reinforcement learning, NPC intelligence, and strategic AI systems used in popular titles. Participants design intelligent agents capable of adapting to dynamic game environments. Real-world case studies like AlphaZero, StarCraft II, and The Last of Us illustrate advanced AI applications.
Scheduled Classes
TOP| 07/24/26 - NVT - Virtual Classroom - Virtual-Instructor Led | (click to enroll)
 |
| 08/21/26 - NVT - Virtual Classroom - Virtual-Instructor Led | (click to enroll)
|
| 09/25/26 - NVT - Virtual Classroom - Virtual-Instructor Led | (click to enroll)
|
| 10/23/26 - NVT - Virtual Classroom - Virtual-Instructor Led | (click to enroll)
|
| 11/20/26 - NVT - Virtual Classroom - Virtual-Instructor Led | (click to enroll)
|
| 12/18/26 - NVT - Virtual Classroom - Virtual-Instructor Led | (click to enroll)
|
What You'll Learn
TOP- Understand AI agent architectures, environments, and behavior models
- Design and implement AI-driven NPCs and decision-making systems in games
- Apply reinforcement learning and search algorithms for adaptive gameplay
- Use pathfinding and movement optimization techniques in 2D and 3D environments
- Analyze case studies to evaluate strategic AI design in modern game development
Outline
TOPUnderstanding AI Agents
- What are AI Agents?
- Agent Architectures and Environments
- Decision Making and Behavior Basics
- Introduction to Multi-Agent Systems
- Case Study: Pac-Man Ghost AI
- Hands On: Build a Basic Reactive AI Agent Navigating a Simple Environment Using Pygame
Introduction to AI Game Agent
- What is an AI Game Agent?
- Key Components of AI Game Agent
- Agent Architectures
- AI Game Agent Behaviors
- Case Study: Racing Games (e.g., Mario Kart, Forza Horizon)
- Hands-On: Creating a Simple Box Movement Game in Playcanvas
Reinforcement Learning in Game Design
- Basics of Reinforcement Learning
- Key Algorithms: Q-Learning and SARSA
- Applying RL to Game Agents
- Challenges and Solutions in Game-based RL
- Case Study: AlphaZero in Games: Mastering Chess, Shogi, and Go through Self-Play and Reinforcement Learning
- Hands On: Train a simple RL agent in OpenAI Gym environment
AI for NPCs and Pathfinding
- Understanding NPCs as AI Agents
- Simple AI Techniques for NPCs
- Pathfinding Algorithms
- Obstacle Avoidance and Movement Optimization
- Case Study
- Hands On
AI for Strategic Decision-Making
- Decision Trees and Minimax for Game AI
- Monte Carlo Tree Search (MCTS) for AI Agent
- Utility-Based Decision Making for Game AI
- AI in Real-Time Strategy (RTS) Games
- Case Study: StarCraft II AI by DeepMind
- Hands-On: Implement a Basic MCTS Agent for Tic-Tac-Toe Using Pygame
Prerequisites
TOPRequired
- Basic Programming Knowledge: Familiarity with coding concepts and languages.
- Game Design Fundamentals: Understanding of core game mechanics and structure.
- Mathematics and Algorithms: Strong grasp of logic and problem-solving techniques.
- Artificial Intelligence Basics: Introductory knowledge of AI principles and models.
- Creative Thinking: Ability to envision dynamic and interactive game elements.
