AI Paper Atlas

Research map / Large language models / Agents, code and math

MarioGPT: Open-Ended Text2Level Generation through Large Language Models

Shyam Sudhakaran, Miguel González-Duque, Matthias Freiberger, Claire Glanois, Elias Najarro, Sebastian Risi

NeurIPS 2023 · Large language models › Agents, code and math · approach: Code generation benchmarks · 25 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune pretrained GPT2 weights rather than train the level model from scratch (ablation)MarioGPT · Mario level validation setTile accuracy: 31% -> 93%Improved
fine-tune pretrained GPT2 weights rather than train the level model from scratch (ablation)MarioGPT · Mario level validation setPath accuracy: 23% -> 91%Improved
replace pretrained-model fine-tuning with an adapter layer (ablation)MarioGPT · Mario level validation setTile accuracy: 93% -> 21%Hurt
replace pretrained-model fine-tuning with an adapter layer (ablation)MarioGPT · Mario level validation setPath accuracy: 91% -> 11%Hurt
condition level generation on natural-language promptsMarioGPT · Prompt-conditioned Mario levelsPrompt accuracy: blocks: 92%Improved
condition level generation on natural-language promptsMarioGPT · Prompt-conditioned Mario levelsPrompt accuracy: enemies: 68%Mixed
increase sampling temperature (ablation)MarioGPT · Generated Mario levelsSample diversityMixed
increase context length beyond 700 (ablation)MarioGPT · Mario level generationPerformanceNo clear effect
use novelty search instead of random-prompt sampling to select diverse levelsNS-MarioGPT · Generated Mario levelsLevel diversityImproved
add novelty search with predicted-path behavior characteristicsNS-MarioGPT · Novelty-search archivePossible coordinates covered: 78%Improved
use model-generated paths as path guidance for level generationMarioGPT · Playable Mario levelsPath MAE: 1.15Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy