DuckMind

a research project: generalizing Sor’s AI engine, providing a multi-layered game-playing agent

overview

DuckMind is a collection of projects that are based on Sor's AI engine, and provides its game-playing AI functionality as a reusable library.

It implements the multi-phase AI system described in my Duck Intelligence presentation^PDF.

Generally, this system is based around the idea of hierarchically combining multiple advanced game-playing AI algorithms into a decision making and action pipeline.

features

the Ducia library provides the core AI algorithms and classes. when using them in external projects, they are typically subclassed for application specific functionality, though many good defaults are provided.

• Framework - Core AI algorithms, including pathfinding, goal-oriented action planning, and utility-based reasoners
• Calc - Mathematical utility classes for AI-related computations
• Cogs - The Personality Engine classes
• Layers - abstract framework for combining multiple Systems in a sense-think-act architecture

usage

read the documentation for detailed information on Ducia's key concepts.

simple example: ants

see the Ants (WIP) example

robust example: ducks

the Sor game makes extensive use of this AI engine, which powers the multi-agent real-time simulation of a bird ecosystem.

in particular, see the AI sources.