Game AI 4N00bz
summary
Covers concrete tricks: uses stims (broadcast stimulus packets), raycasts, cone vision and navmesh heatmaps to fake sensing; composes behavior from reusable patterns inside finite state machines, behavior trees or a lightweight utility matrix for large crowds; constrains emergent chaos with volumes and smart objects that override NPC brains; shows practical tradeoffs (why ML rarely ships), a six‑variable “memory” trick used in Shadow of Mordor, and recommends Unreal Blueprints for iterative boss fights.
AI-written summary · about
chapters (22)
- 0:00Start
- 2:09Agent Depth
- 3:34Agent Categories in Gameplay
- 4:12Artificial Agents
- 6:45Human Computer Interaction Loop
- 7:33How Does It Work for Ai
- 9:06Perception
- 9:26Game State versus Game View
- 13:19Raycast
- 13:52Kuna Vision
- 15:16Death Count
- 17:59Focus of Your Ai
- 18:11Dominant Dynamics
- 27:58Visual Scripting
- 29:13Behavior Trees
- 31:02Utility Matrix
- 33:26Finite State Machines
- 39:49Archetypes
- 48:13Contextual Overrides
- 50:02Smart Objects
- 51:36Contextual Override
- 52:25Relatableness
related talks
01h 01mThe Forgotten AI of Video Games
46mMind your NPCs and Q’s: what’s next for Game AI?
52mThe Journey of AI in Games: A Technical and Philosophical overview
39mEmbarrassing Mistakes: a short story about AI
01h 01mIntroduction to Practical AI
15mGaming the Future of Architecture
29mThe Present & Future of AI and Games
48mMachine Takeover - Improving Your Game With Machine Learning & AI