This Saturday, there are five interesting Smart Links for you about game development and artificial intelligence! Feel free to contact me if you have any news or tips for next week.
Reinforcement Learning and Real-Time Strategy
There’s a competition for applying RL to a variety different problems, including RTS games. Since November 1st, you can now download the framework and start training your agents. This part of the competition is described in detail by Marc Lanctot from the University of Alberta. Follow the link for more instructions, and let us know if you sign up!
On Sensory Systems and Flocking
Vincent Tan muses about his implementation of sensory systems:
“I think of AI more in terms of simulation. How can a certain behavior be simulated? How can a certain phenomena be simulated? For example, flock behavior can be simulated using simple rules yet resulting in complex patterns. I’ve even tried my hand at computer virus simulations.”
Getting Started in Game Design with AI
Soren Johnson explains how focusing on artificial intelligence, among eight other tips, is a good way to start as a career as a game designer.
Controlling In-Game Inflation with AI
Dusan Writer wrote an interesting post about the economies in online worlds, with this particular insight about using AI to help control the financial simulation:
“[Edward Castranova] argues that a combination of using Artificial Intelligence (non-player characters) and control of the flow of objects into the world allows developers to control for MUDflation.”
Quite a fascinating and unique application for game AI!
Dave Mark’s Observations on Game AI
Dave Mark has started a new blog where he posts observations and analyses of the AI techniques in games. You might recognize him from his insightful comments here at AiGameDev.com. Dave is a game AI consultant, independent game developer, and AI Game Programming Wisdom 4 (see Amazon US, UK) co-author.
Mario Kart: Double Dash — AI Review
Dave Mark’s first post is a review of the AI in Mario Kart: Double Dash after playing it extensively! He covers topics like the state machines, racing lines, rubber banding, and fixing some little bugs with additional steering forces.
Game AI, or Do game AI’s feel pain?
Zeroth brainstorms ways to design the AI for his RPG game:
“Here is one possible idea, similar in aspect to a genetic algorithm. Each enemy has a fear and an intelligence rating, randomly assigned within a predetermined racial standard deviation.”
Stay tuned next Saturday for more Smart Links from around the web.