Interactive tool lets developers teach NPCs behavior inside Minecraft

Demonstration of MANA: Multi-perspective Alignment of NPC Agents

Human-Computer Interaction

Summary

Creating believable characters in games is hard because programmers must write lots of detailed instructions. The authors introduce MANA, a tool that lets developers directly show how a character should act by controlling it from that character’s point of view while playing Minecraft. MANA then learns from these demonstrations to create general behavior rules that the NPC can use on its own later. This approach made two NPCs act consistently and believably after just a couple of minutes of demonstration.

What this means in practice

Authors

Amir Tahmasbi, Keshav Singh, Shaheer Raza, Owen Mei, Jason Wu

Abstract

We present MANA (Multi-perspective Alignment of NPC Agents), an interactive approach for authoring NPC behavior through embodied demonstration. We show MANA in the context of Minecraft, where a developer aligns NPCs while playing the game itself. Activating MANA lets the developer dynamically switch into the point of view (POV) of any character and demonstrate, in-situ, how it would act given the surrounding context, through both movement and dialogue. MANA then distills each demonstration into a generalized policy that maps in-game context to actions. Finally, once the developer switches to another NPC or exits MANA mode, this generalized policy drives the NPC on its own. We demonstrate MANA by aligning two initially generic Minecraft NPCs: Fletcher and Farmer to act aggressively and cowardly, respectively. After roughly 2 minutes of in-game play, each character exhibits consistent and believable behaviors across new, unseen scenarios.