mlsanityData to 14 Oct 2026

Learning Controllable Content Generators

arXiv 2105.02993 ↗First posted 6 May 2021cs.LG cs.AIcited by 40

Not on the map. Why?

Abstract (arXiv)

It has recently been shown that reinforcement learning can be used to train generators capable of producing high-quality game levels, with quality defined in terms of some user-specified heuristic. To ensure that these generators' output is sufficiently diverse (that is, not amounting to the reproduction of a single optimal level configuration), the generation process is constrained such that the initial seed results in some variance in the generator's output. However, this results in a loss of control over the generated content for the human user. We propose to train generators capable of producing controllably diverse output, by making them "goal-aware." To this end, we add conditional inputs representing how close a generator is to some heuristic, and also modify the reward mechanism to incorporate that value. Testing on multiple domains, we show that the resulting level generators are capable of exploring the space of possible levels in a targeted, controllable manner, producing levels of comparable quality as their goal-unaware counterparts, that are diverse along designer-specified dimensions.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

15 of 22 references.

References · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 275
  3. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 137
  4. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 119
  5. 2018Learning to Navigate in Cities Without a Mapcited by 104
  6. 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
  7. 2016Multi-Objective Deep Reinforcement Learningcited by 83
  8. 2018Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generationcited by 81
  9. 2018Evolving Mario Levels in the Latent Space of a Deep Convolutional Generative Adversarial Networkcited by 76
  10. 2020Deep Learning for Procedural Content Generationcited by 73
  11. 2020Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Textcited by 59
  12. 2018General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithmscited by 45
3 more
  1. 2021Adversarial Reinforcement Learning for Procedural Content Generationcited by 36
  2. 2020Mixed-Initiative Level Design with RL Brushcited by 13
  3. 2020Using Fractal Neural Networks to Play SimCity 1 and Conway's Game of Life at Variable Scalescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 11; 2023: 9; 2024: 6; 2025: 9; 2026: 2.

40 papers.

Sort:

By area:

  1. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  2. 2022Evolving Curricula with Regret-Based Environment Designcited by 173
  3. 2023Level Generation Through Large Language Modelscited by 68
  4. 2023ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfercited by 50
  5. 2022Deep Surrogate Assisted Generation of Environmentscited by 40
  6. 2024Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpaintingcited by 38
  7. 2021Illuminating Diverse Neural Cellular Automata for Level Generationcited by 35
  8. 2022Learning Controllable 3D Level Generatorscited by 19
  9. 2022Path of Destruction: Learning an Iterative Level Generator Using a Small Datasetcited by 14
  10. 2023Games for Artificial Intelligence Research: A Review and Perspectivescited by 14
  11. 2024DreamGarden: A Designer Assistant for Growing Games from a Single Promptcited by 10
  12. 2022Mutation Models: Learning to Generate Levels by Imitating Evolutioncited by 9
28 more
  1. 2023RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Gamescited by 7
  2. 2024PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generatorscited by 7
  3. 2022Latent Prompt Tuning for Text Summarizationcited by 6
  4. 2021Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)cited by 5
  5. 2024Measuring Diversity of Game Scenarioscited by 5
  6. 2023Hierarchically Composing Level Generators for the Creation of Complex Structurescited by 4
  7. 2023Balancing of competitive two-player Game Levels with Reinforcement Learningcited by 4
  8. 2024G-PCGRL: Procedural Graph Data Generation via Reinforcement Learningcited by 4
  9. 2025IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generationcited by 4
  10. 2025PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learningcited by 3
  11. 2025Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RLcited by 3
  12. 2021Adapting Procedural Content Generation to Player Personas Through Evolutioncited by 2
  13. 2022Online Game Level Generation from Musiccited by 2
  14. 2022Aesthetic Bot: Interactively Evolving Game Maps on Twittercited by 2
  15. 2022Start Small: Training Controllable Game Level Generators without Training Data by Learning at Multiple Sizescited by 2
  16. 2025Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representationcited by 2
  17. 2022State Space Closure: Revisiting Endless Online Level Generation via Reinforcement Learningcited by 1
  18. 2023Controllable Path of Destructioncited by 1
  19. 2023Tree-Based Reconstructive Partitioning: A Novel Low-Data Level Generation Approachcited by 1
  20. 2023PCGPT: Procedural Content Generation via Transformerscited by 1
  21. 2025Video Game Level Design as a Multi-Agent Reinforcement Learning Problemcited by 1
  22. 2026Improving Regret Approximation for Unsupervised Dynamic Environment Generationcited by 1
  23. 2024Improving Conditional Level Generation using Automated Validation in Match-3 Gamescited by 0
  24. 2025Simulation-Driven Balancing of Competitive Game Levels with Reinforcement Learningcited by 0
  25. 2025Level the Level: Balancing Game Levels for Asymmetric Player Archetypes With Reinforcement Learningcited by 0
  26. 2025A Markovian Framing of WaveFunctionCollapse for Procedurally Generating Aesthetically Complex Environmentscited by 0
  27. 2025Expanding Horizons of Level Diversity via Multi-objective Evolutionary Learningcited by 0
  28. 2026Learning Local Constraints for Reinforcement-Learned Content Generatorscited by 0