PCGPT: Procedural Content Generation via Transformers

TL;DR

PCGPT introduces a transformer-based framework for procedural content generation that produces diverse, complex game levels efficiently by modeling action trajectories and leveraging self-attention, demonstrated in Sokoban puzzles.

Contribution

The paper presents a novel transformer-based approach to PCG using offline reinforcement learning, improving content diversity and complexity with fewer steps than prior methods.

Findings

Generates more complex and diverse game levels.

Achieves results in fewer steps compared to existing methods.

Outperforms previous PCG approaches in Sokoban.

Abstract

The paper presents the PCGPT framework, an innovative approach to procedural content generation (PCG) using offline reinforcement learning and transformer networks. PCGPT utilizes an autoregressive model based on transformers to generate game levels iteratively, addressing the challenges of traditional PCG methods such as repetitive, predictable, or inconsistent content. The framework models trajectories of actions, states, and rewards, leveraging the transformer's self-attention mechanism to capture temporal dependencies and causal relationships. The approach is evaluated in the Sokoban puzzle game, where the model predicts items that are needed with their corresponding locations. Experimental results on the game Sokoban demonstrate that PCGPT generates more complex and diverse game content. Interestingly, it achieves these results in significantly fewer steps compared to existing methods, showcasing its potential for enhancing game design and online content generation. Our model represents a new PCG paradigm which outperforms previous methods.