mlsanityData to 13 Oct 2026

PCGPT: Procedural Content Generation via Transformers

arXiv 2310.02405 ↗First posted 3 Oct 2023cs.LG cs.AIcited by 1

On the map: Offline RL and imitation learning from data → Decision transformers and sequence modeling

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Placed in Decision transformers and sequence modeling, one of 13 directions in Offline RL and imitation learning from data. Builds on 29 of its 48 references that are in the map. First posted on arXiv 3 Oct 2023.

Builds on

29 of 48 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Multi-Game Decision Transformers30 May
  2. 2021Decision Transformer: Reinforcement Learning via Sequence Modeling2 Jun

Other references · 27

  1. 2017Attention Is All You Needcited by 60,106
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  4. 2020End-to-End Object Detection with Transformerscited by 7,396
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,539
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,284
  7. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,281
  8. 2013Playing Atari with Deep Reinforcement Learningcited by 3,221
  9. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,889
  10. 2018Self-Attention Generative Adversarial Networkscited by 809
  11. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 699
  12. 2022Transformers in Time Series: A Surveycited by 493
15 more
  1. 2021Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemblecited by 211
  2. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 136
  3. 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
  4. 2021Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuningcited by 82
  5. 2020Deep Learning for Procedural Content Generationcited by 73
  6. 2023Level Generation Through Large Language Modelscited by 68
  7. 2019Increasing Generality in Machine Learning through Procedural Content Generationcited by 58
  8. 2018Optimizing Agent Behavior over Long Time Scales by Transporting Valuecited by 57
  9. 2021Learning Controllable Content Generatorscited by 40
  10. 2021Adversarial Reinforcement Learning for Procedural Content Generationcited by 36
  11. 2019Bootstrapping Conditional GANs for Video Game Level Generationcited by 35
  12. 2021Reinforcement Learning for Education: Opportunities and Challengescited by 25
  13. 2020Learning to Generate Levels From Nothingcited by 17
  14. 2020Conditional Level Generation and Game Blendingcited by 17
  15. 2019Transformer Based Reinforcement Learning For Gamescited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integrationcited by 22

Similar, not cited

Close in wording, no citation either way

  1. 2024Moonshine: Distilling Game Content Generators into Steerable Generative Models
  2. 2025PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning
  3. 2024Zero-Shot Reasoning: Personalized Content Generation Without the Cold Start Problem
  4. 2025Zero-shot 3D Map Generation with LLM Agents: A Dual-Agent Architecture for Procedural Content Generation
  5. 2025Model as a Game: On Numerical and Spatial Consistency for Generative Games
  6. 2025Position: Interactive Generative Video as Next-Generation Game Engine
  7. 2024Playable Game Generation
  8. 2026Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness