mlsanityData to 7 Oct 2026

Learning Controllable 3D Level Generators

arXiv 2206.13623 ↗First posted 27 Jun 2022cs.AI cs.LG cs.NEcited by 19

Not on the map. Why?

Abstract (arXiv)

Procedural Content Generation via Reinforcement Learning (PCGRL) foregoes the need for large human-authored data-sets and allows agents to train explicitly on functional constraints, using computable, user-defined measures of quality instead of target output. We explore the application of PCGRL to 3D domains, in which content-generation tasks naturally have greater complexity and potential pertinence to real-world applications. Here, we introduce several PCGRL tasks for the 3D domain, Minecraft (Mojang Studios, 2009). These tasks will challenge RL-based generators using affordances often found in 3D environments, such as jumping, multiple dimensional movement, and gravity. We train an agent to optimize each of these tasks to explore the capabilities of previous research in PCGRL. This agent is able to generate relatively complex and diverse levels, and generalize to random initial states and control targets. Controllability tests in the presented tasks demonstrate their utility to analyze success and failure for 3D generators.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 27 Jun 2022.

Builds on

19 of 34 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 260
  3. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  4. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 136
  5. 2021Replay-Guided Adversarial Environment Designcited by 108
  6. 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
  7. 2019Covariance Matrix Adaptation for the Rapid Illumination of Behavior Spacecited by 78
  8. 2018Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Networkcited by 76
  9. 2021Learning Controllable Content Generatorscited by 40
  10. 2019Bootstrapping Conditional GANs for Video Game Level Generationcited by 35
  11. 2021Illuminating Diverse Neural Cellular Automata for Level Generationcited by 35
  12. 2019Mapping Hearthstone Deck Spaces through MAP-Elites with Sliding Boundariescited by 32
7 more
  1. 2020EvoCraft: A New Challenge for Open-Endednesscited by 23
  2. 2018Co-Creative Level Design via Machine Learningcited by 18
  3. 2020Learning to Generate Levels From Nothingcited by 17
  4. 2020Mixed-Initiative Level Design with RL Brushcited by 13
  5. 2020Multi-Objective level generator generation with Marahelcited by 8
  6. 2018Q-DeckRec: A Fast Deck Recommendation System for Collectible Card Gamescited by 5
  7. 2021Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)cited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 6; 2025: 7; 2026: 2.

19 papers.

Sort:

  1. 2024DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraftcited by 17
  2. 2024DreamGarden: A Designer Assistant for Growing Games from a Single Promptcited by 10
  3. 2023RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Gamescited by 7
  4. 2024PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generatorscited by 7
  5. 2024Measuring Diversity of Game Scenarioscited by 5
  6. 2025The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in Gamescited by 5
  7. 2023Hierarchically Composing Level Generators for the Creation of Complex Structurescited by 4
  8. 2023Balancing of competitive two-player Game Levels with Reinforcement Learningcited by 4
  9. 2024G-PCGRL: Procedural Graph Data Generation via Reinforcement Learningcited by 4
  10. 2025IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generationcited by 4
  11. 20243D Building Generation in Minecraft via Large Language Modelscited by 3
  12. 2025PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learningcited by 3
7 more
  1. 2025Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RLcited by 3
  2. 2023Generating Redstone Style Cities in Minecraftcited by 2
  3. 2025Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representationcited by 2
  4. 2025Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learningcited by 0
  5. 2025Level the Level: Balancing Game Levels for Asymmetric Player Archetypes With Reinforcement Learningcited by 0
  6. 2026High Dimensional Procedural Content Generationcited by 0
  7. 2026Learning Local Constraints for Reinforcement-Learned Content Generatorscited by 0