AI+ Gaming

Prerequisites

• Basic Programming Skills – Comfortable with Python or similar languages.
• Foundational Math Knowledge – Understanding of linear algebra and probability.
• Intro to Machine Learning – Familiarity with ML concepts and algorithms.
• Game Development Exposure – Experience with Unity or Unreal Engine basics.
• Problem-Solving Mindset – Ability to approach challenges creatively and logically.

Course outline

1. 1

   Lesson 1: Introduction to AI in Games

   • 1.1 What is AI?
   • 1.2 Evolution of AI in the Gaming Industry
   • 1.3 Types of AI in Games
   • 1.4 Benefits, Challenges, and Innovations in Game AI
2. 2

   Lesson 2: Game Design Principles using AI

   • 2.1 Understanding Game Mechanics and Player Experience
   • 2.2 Role of AI in Gameplay and Narrative Design
   • 2.3 Designing Game Environments for AI Interaction
   • 2.4 AI-Driven Behavior vs Traditional Scripted Logic
   • 2.5 Case Study: Dynamic AI and Narrative Adaptation in Middle earth: Shadow of Mordor
   • 2.6 Hands-On Exercise: Designing Adaptive NPC Behavior and Environment Interaction
3. 3

   Lesson 3: Foundations of AI in Gaming

   • 3.1 Core AI Concepts for Gaming
   • 3.2 Search Algorithms and Pathfinding
   • 3.3 AI Behavior Modeling and Procedural Content Generation (PCG)
   • 3.4 Introduction to Machine Learning and Reinforcement Learning
   • 3.5 Case Study: AI in Minecraft — Procedural Content Generation and Agent Navigation
   • 3.6 Hands-On: Implementing A* Pathfinding and FSM for NPC Behavior
4. 4

   Lesson 4: Reinforcement Learning Fundamentals

   • 4.1 Core Concepts: States, Actions, Rewards, Policies, Q-Learning:
   • 4.2 Exploration versus Exploitation in Learning Systems:
   • 4.3 Overview of Deep Q Networks (DQN) and Policy Gradient Methods
   • 4.4 Case Study: Reinforcement Learning in DeepMind’s AlphaGo
   • 4.5 Hands-On: Train a Reinforcement Learning Model on OpenAI Gym’s GridWorld
5. 5

   Lesson 5: Planning and Decision Making in Games

   • 5.1 Minimax Algorithm and Alpha-Beta Pruning
   • 5.2 Monte Carlo Tree Search (MCTS)
   • 5.3 Applications in Board Games and Real-Time Strategy (RTS) Games
   • 5.4 Case Study: Strategic AI in StarCraft II – Combining Planning Algorithms for Real-Time Strategy
   • 5.5 Hands-on Implementation: Guides on implementing the Minimax algorithm for Tic-Tac-Toe
6. 6

   Lesson 6: AI Techniques in 2D/3D Virtual Gaming Environments Basic

   • 6.1 Overview of 2D and 3D Game Environments
   • 6.2 Environment Representation Techniques
   • 6.3 Navigation and Pathfinding in 2D/3D Spaces
   • 6.4 Interaction and Behavior Systems in Virtual Environments
   • 6.5 Case Study: Navigation and Interaction AI in The Legend of Zelda: Breath of the Wild
   • 6.6 Hands-On: Building Basic Navigation and Interaction in 2D and 3D Game Environments
7. 7

   Lesson 7: Adaptive Systems and Dynamic Difficulty

   • 7.1 Adaptive Systems Overview
   • 7.2 Dynamic Difficulty Adjustment (DDA) Principles
   • 7.3 Adaptive Storytelling, Personalization, and Player Profiling
   • 7.4 AI Techniques in Adaptive Systems
   • 7.5 Implementation Strategies and Tools
   • 7.6 Case Study: Dynamic Enemy Management and Replayability with Left 4 Dead’s AI Director
   • 7.7 Hands-On: Developing an Adaptive Dynamic Difficulty System in Unity
8. 8

   Lesson 8: Future of AI in Gaming

   • 8.1 Generalist AI Agents and Transfer Learning
   • 8.2 AI-Powered Game Design and Testing Tools
   • 8.3 Ethical Considerations and AI Transparency
   • 8.4 Emerging Technologies: VR/AR AI and AI in Esports Coaching
9. 9

   Lesson 9: Capstone Project

   • Cable, Fiber, DSL, or LEO Satellite (i.e. Starlink) internet with speeds of at least 10mb/sec download and 5mb/sec upload are recommended for the best experience.