mlsanityData to 13 Oct 2026

PCGRL: Procedural Content Generation via Reinforcement Learning

arXiv 2001.09212 ↗First posted 24 Jan 2020cs.LG cs.AI stat.MLcited by 90

Not on the map. Why?

Abstract (arXiv)

We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design is framed as a game, and the content generator itself is learned. By seeing the design problem as a sequential task, we can use reinforcement learning to learn how to take the next action so that the expected final level quality is maximized. This approach can be used when few or no examples exist to train from, and the trained generator is very fast. We investigate three different ways of transforming two-dimensional level design problems into Markov decision processes and apply these to three game environments.

Key facts. Cited by 90 papers in the map (data through 13 Oct 2026). First posted on arXiv 24 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 16; 2022: 18; 2023: 18; 2024: 10; 2025: 21; 2026: 7.

90 papers.

Sort:

By area:

  1. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 371
  2. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 181
  3. 2022Evolving Curricula with Regret-Based Environment Designcited by 168
  4. 2023Level Generation Through Large Language Modelscited by 68
  5. 2021Learning Controllable Content Generatorscited by 40
  6. 2022Deep Surrogate Assisted Generation of Environmentscited by 40
  7. 2024Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpaintingcited by 38
  8. 2021Adversarial Reinforcement Learning for Procedural Content Generationcited by 36
  9. 2021Illuminating Diverse Neural Cellular Automata for Level Generationcited by 35
  10. 2021Experience-Driven PCG via Reinforcement Learning: A Super Mario Bros Studycited by 25
  11. 2021Reinforcement Learning for Education: Opportunities and Challengescited by 25
  12. 2023Beyond Prompts: Exploring the Design Space of Mixed-Initiative Co-Creativity Systemscited by 20
38 more
  1. 2022Learning Controllable 3D Level Generatorscited by 19
  2. 2024DreamCraft: Text-Guided Generation of Functional 3D Environments in Minecraftcited by 17
  3. 2021World-GAN: a Generative Model for Minecraft Worldscited by 14
  4. 2022Path of Destruction: Learning an Iterative Level Generator Using a Small Datasetcited by 14
  5. 2023Games for Artificial Intelligence Research: A Review and Perspectivescited by 14
  6. 2023Reinforcement Learning for Generative AI: A Surveycited by 11
  7. 2024DreamGarden: A Designer Assistant for Growing Games from a Single Promptcited by 10
  8. 2021Situated Dialogue Learning through Procedural Environment Generationcited by 9
  9. 2022Mutation Models: Learning to Generate Levels by Imitating Evolutioncited by 9
  10. 2022Creative Wand: A System to Study Effects of Communications in Co-Creative Settingscited by 9
  11. 2025G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibrationcited by 8
  12. 2022Generative Personas That Behave and Experience Like Humanscited by 7
  13. 2023RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Gamescited by 7
  14. 2024Grammar-based Game Description Generation using Large Language Modelscited by 7
  15. 2024PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generatorscited by 7
  16. 2021Go-Blend behavior and affectcited by 6
  17. 2025The Procedural Content Generation Benchmark: An Open-source Testbed for Generative Challenges in Gamescited by 6
  18. 2021Discovering Generalizable Skills via Automated Generation of Diverse Taskscited by 5
  19. 2021Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)cited by 5
  20. 2024ChatPCG: Large Language Model-Driven Reward Design for Procedural Content Generationcited by 5
  21. 2025LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generationcited by 5
  22. 2023Hierarchically Composing Level Generators for the Creation of Complex Structurescited by 4
  23. 2023Balancing of competitive two-player Game Levels with Reinforcement Learningcited by 4
  24. 2023Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rulescited by 4
  25. 2024G-PCGRL: Procedural Graph Data Generation via Reinforcement Learningcited by 4
  26. 2025IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generationcited by 4
  27. 2021Dynamic Difficulty Adjustment in Virtual Reality Exergames through Experience-driven Procedural Content Generationcited by 3
  28. 2022Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AIcited by 3
  29. 2022Active Task Randomization: Learning Robust Skills via Unsupervised Generation of Diverse and Feasible Taskscited by 3
  30. 2024Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversitycited by 3
  31. 2025PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learningcited by 3
  32. 2025Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RLcited by 3
  33. 2025Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularizationcited by 3
  34. 2021Keiki: Towards Realistic Danmaku Generation via Sequential GANscited by 2
  35. 2021Procedural Content Generation using Behavior Trees (PCGBT)cited by 2
  36. 2022Watts: Infrastructure for Open-Ended Learningcited by 2
  37. 2022Online Game Level Generation from Musiccited by 2
  38. 2022Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizescited by 2

50 most cited of 90 All 90 (JSON)