Learning Controllable Content Generators
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625
Search-Based Procedural Content Generation: A Taxonomy and Survey
Togelius, J., Yannakakis, G. N., Stanley, K. O., & Browne, C. (2011) · IEEE Transactions on Computational Intelligence and AI in Games · doi:10.1109/tciaig.2011.2148116 · Cited by 706
Self-citationPCGRL: Procedural Content Generation via Reinforcement Learning
Khalifa, A., Bontrager, P., Earle, S., & Togelius, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v16i1.7416 · Cited by 156
Self-citationEmergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
Dennis, M., Jaques, N., Vinitsky, E., Bayen, A., Russell, S., Critch, A., & Levine, S. (2020) · arXiv · doi:10.48550/arxiv.2012.02096 · Cited by 60
Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
Portelas, R., Colas, C., Hofmann, K., & Oudeyer, P.-Y. (2019) · arXiv · doi:10.48550/arxiv.1910.07224 · Cited by 59
Cited by
Simulation-Driven Balancing of Competitive Game Levels With Reinforcement Learning
Rupp, F., Eberhardinger, M., & Eckert, K. (2024) · IEEE Transactions on Games · doi:10.1109/tg.2024.3399536 · Cited by 11
“We refrain from implementing a single but controllable approach as in [34], as we are only experimenting with different parameterizations of the reward function.”
InfluentialBalancing of competitive two-player Game Levels with Reinforcement Learning
Rupp, F., Eberhardinger, M., & Eckert, K. (2023) · 2023 IEEE Conference on Games (CoG) · doi:10.1109/cog57401.2023.10333248 · Cited by 10
Level the Level: Balancing Game Levels for Asymmetric Player Archetypes With Reinforcement Learning
Rupp, F., & Eckert, K. (2025) · Proceedings of the 20th International Conference on the Foundations of Digital Games · doi:10.1145/3723498.3723747 · Cited by 1
“Other works extend PCGRL for controllability [3], 3D levels [5], graph data [14], and scalability [4].”
Metadata
- Authors
- Earle, S., Edwards, M., Khalifa, A., Bontrager, P., & Togelius, J.
- Venue
- 2021 IEEE Conference on Games (CoG)
- Publisher
- IEEE
- Published
- 2021-08-17
- Pages
- 1-9
- OpenAlex
- W4205590214
- Cited by
- 41
- References
- 5
- FWCI
- 3.95
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning Controllable Content Generators. https://app.cochat.ai/papers/10.1109/cog52621.2021.9619159
- The paper
- Earle, S., Edwards, M., Khalifa, A., Bontrager, P., & Togelius, J. (2021). Learning Controllable Content Generators. 2021 IEEE Conference on Games (CoG). https://doi.org/10.1109/cog52621.2021.9619159
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.