MarioMix: Creating Aligned Playstyles for Bots with Interactive Reinforcement Learning

TL;DR

MarioMix is a user-friendly framework that allows game developers to create and customize bot playstyles in Super Mario Bros. using interactive reinforcement learning, without requiring machine learning expertise.

Contribution

It introduces a novel interactive RL-based tool enabling non-experts to design aligned bot behaviors for games.

Findings

Effective in creating diverse playstyles

Validated with industry game designers

Accessible to non-technical users

Abstract

In this paper, we propose a generic framework that enables game developers without knowledge of machine learning to create bot behaviors with playstyles that align with their preferences. Our framework is based on interactive reinforcement learning (RL), and we used it to create a behavior authoring tool called MarioMix. This tool enables non-experts to create bots with varied playstyles for the game titled Super Mario Bros. The main interaction procedure of MarioMix consists of presenting short clips of gameplay displaying precomputed bots with different playstyles to end-users. Then, end-users can select the bot with the playstyle that behaves as intended. We evaluated MarioMix by incorporating input from game designers working in the industry.