I describe work in progress on a system for interactiveprototyping of AI-based characters. A sort of "Sims construction set," the system combines a simple physics simulation with a set of domain-specific languages to allow programmers to quickly build and test character AI. It allows iterative, incremental development in which behaviors can be compactly authored, tested, monitored, and hot-swapped for new behaviors, using in-game editing and debugging facilities.

We examine the use of constraint propagation for populating indoor game levels with enemies and other objects. We introduce a notion of path constraints, which bound some function over the possible paths a player might take, and show how to efficiently place objects while guaranteeing path constraints. This allows the system to guarantee that power-ups are balanced to the number of enemies occurring in the level, that they're placed early enough to be useful, that keys are not hidden behind the doors they are intended to unlock, and so on. We describe a constraint solver based on interval methods that allows natural processing of numeric constraints and show that it is efficient enough to be used even on very low-end platforms.

Making a game that supports generative conversation with NPCs involves a number of technical and design challenges, ranging from designing new game mechanics to making a Prolog interpreter run under Unity. I discuss the software architecture of a game, scheduled for initial release in spring 2015, that attempts to solve some of these problems.

Reasoning using expressive symbolic representations is a central theme of AI research, yet there are surprisingly few deployed games, even within the AIIDE research community, that use this sort of "classical" AI. This is partly due to practical and methodological issues, but also due to fundamental mismatches between current game genres and classical AI systems. I will argue that if we want to build games that leverage high-end classical AI techniques like commonsense reasoning and natural language processing, we will also have to develop new game genres and mechanics that better exploit those capabilities. I will also present a design sketch of a game that explores potential game mechanics for classical AI.

MKULTRA is an experimental game that explores novel AI-based game mechanics. Similar in some ways to text-based interactive fiction, the player controls a character who interacts with other characters through dialog. Unlike traditional IF, MKULTRA characters have simple natural language understanding and generation capabilities, sufficient to answer questions and carry out simple tasks. The game explores a novel game mechanic, belief injection, in which players can manipulate the behavior of NPCs by injecting false beliefs into their knowledge bases. This allows for an unusual form of puzzle-based gameplay, in which the player must understand the beliefs and motivational structure of the characters well enough to understand what beliefs to inject.

Players in Dear Leader's Happy Story Time are placed in the role of contestants in a reality TV show where they are forced to audition for roles in the upcoming film of the host, a deranged billionaire who has inexplicably been elected president. The stories are produced by a story generator that combines stock plots and characters to produce kitsch story outlines. The players then collaborate to improvise a camp performance of the outline. The game design provides a context for experimenting with automatic story generation within a narrative game, as well as an opportunity for experimenting with knowledge representation schemes for expressing the tropes of popular narrative. The story generator uses a higher-order logic for describing tropes, and an HTN planning algorithm based on Nau et al.'s SHOP.

Answer-set programming (ASP), a family of SAT-based logic programming systems, is attractive for procedural content generation.