Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Balancing of competitive two-player Game Levels with Reinforcement Learning

Open access
Rupp, Florian, Eberhardinger, Manuel, Eckert, Kai · 2023 · 2023 IEEE Conference on Games (CoG)

Abstract

The balancing process for game levels in a competitive two-player context involves a lot of manual work and testing, particularly in non-symmetrical game levels. In this paper, we propose an architecture for automated balancing of tile-based levels within the recently introduced PCGRL framework (procedural content generation via reinforcement learning).Our architecture is divided into three parts: (1) a level generator, (2) a balancing agent and, (3) a reward modeling simulation. By playing the level in a simulation repeatedly, the balancing agent is rewarded for modifying it towards the same win rates for all players. To this end, we introduce a novel family of swap-based representations to increase robustness towards playability. We show that this approach is capable to teach an agent how to alter a level for balancing better and faster than plain PCGRL. In addition, by analyzing the agent’s swapping behavior, we can draw conclusions about which tile types influence the balancing most. We test and show our results using the Neural MMO (NMMO) environment in a competitive two-player setting.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cog57401.2023.10333248

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 In our game environment, two players must forage for resources like food (dark green) and water (blue) to survive longest. By swapping the highlighted tiles, the trained model reached a more balanced game in simulated game runs.
Fig. 1 In our game environment, two players must forage for resources like food (dark green) and water (blue) to survive longest. By swapping the highlighted tiles, the trained model reached a more balanced game in simulated game runs.CC-BY · From the PDF
Fig. 3 Description of the balancing architecture. It is separated into three units: A level generator, a level balancing agent and a level playing simulation. In the latter, the game is simulated by playing it n -times with player agents. The reward r t for training the balancing agent is calculated out of the balancing states b t and b t -1 from the simulations.
Fig. 3 Description of the balancing architecture. It is separated into three units: A level generator, a level balancing agent and a level playing simulation. In the latter, the game is simulated by playing it n -times with player agents. The reward r t for training the balancing agent is calculated out of the balancing states b t and b t -1 from the simulations.CC-BY · From the PDF
Fig. 4 How many times n should we run the simulation to approximate the balancing state? We figure that out by calculating the mean deviation µ n of win rates from n -2 to n for the investigation of fluctuations in win rates.
Fig. 4 How many times n should we run the simulation to approximate the balancing state? We figure that out by calculating the mean deviation µ n of win rates from n -2 to n for the investigation of fluctuations in win rates.CC-BY · From the PDF
Image 4
CC-BY · From the PDF
Image 5
CC-BY · From the PDF
Image 6
CC-BY · From the PDF
Image 7
CC-BY · From the PDF
Fig. 8 Comparing the swapped tiles by the model per representation on the generated 1000 levels. The comparison is made in relation to the inverse tile type distribution of all levels. This shows the difference to random swapping.
Fig. 8 Comparing the swapped tiles by the model per representation on the generated 1000 levels. The comparison is made in relation to the inverse tile type distribution of all levels. This shows the difference to random swapping.CC-BY · From the PDF

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.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

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

Show all 27 references

Research works printed but not linked: 1

  1. Mojang, 2011, Mincraft

Cited by

See all 10

Metadata

Authors
Rupp, F., Eberhardinger, M., & Eckert, K.
Affiliations
  • Technische Hochschule Mannheim (DE)
  • Stuttgart Media University (DE)
Venue
2023 IEEE Conference on Games (CoG)
Publisher
IEEE
Published
2023-08-21
Pages
1-8
OpenAlex
W4389296253
Cited by
10
References
27
Citations by year
2026: 1 · 2025: 2 · 2024: 7
FWCI
1.78
Type
conference paper
Language
en
Open access
Locations
  • IEEE Conference on Games (CoG) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
Volkswagen Foundation
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
  • Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
  • Social Sciences › Sociology and Political Science › Digital Games and Media
Keywords
procedural content generation, reinforcement learning, reward modeling

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: Balancing of competitive two-player Game Levels with Reinforcement Learning. https://app.cochat.ai/papers/10.1109/cog57401.2023.10333248
The paper
Rupp, F., Eberhardinger, M., & Eckert, K. (2023). Balancing of competitive two-player Game Levels with Reinforcement Learning. 2023 IEEE Conference on Games (CoG). https://doi.org/10.1109/cog57401.2023.10333248

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.