Roguelike Intelligence

Roguelike Game AI overview

Since I'm an AI engineer, and since I'm unemployed right now, and since I'm interested in roguelike games, I thought I'd write a series of articles on game AI for roguelikes as a contribution to the community.

Some of these techniques (Stateless AI's and State Machines in particular) are properly "pseudointelligence" rather than "artificial intelligence", because they don't involve any actual learning. But "AI" is how game designers refer to the decision-making code for their artificial antagonists, regardless of its actual status, so I'm going to use it.

The ground I plan to cover here includes roughly these articles; I may add an article or two to this or change the order of articles depending on what people are interested in reading.

1. Stateless AI
2. State Machine AI
3. "Evolving" stateless AI's or state machine AI's
4. Modeling the player
5. Minimaxing in application to roguelike domains
6. Neural Networks and training them with backprop
7. "Evolving" neural networks.
8. Recurrent Neural Networks (NN's with memory).

Overview

• Roguelike Intelligence, part 1 - Stateless AI's
• Roguelike Intelligence, part 2A - Intrinsic Information and State Machine AIs
• Roguelike Intelligence, part 2B - Displaced Actions
• Roguelike Intelligence, part 3A - Genetic Algorithms and Evolving State Machine AIs
• Roguelike Intelligence, part 3B - Evolving State Machine AIs

Ray Dillinger