Automated Video Game Testing Using Synthetic and Humanlike Agents
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
In this article, we present a new methodology that employs tester agents to automate video game testing. We introduce two types of agents - synthetic and humanlike - and two distinct approaches to create them. Our agents are derived from Sarsa and Monte Carlo tree search (MCTS) but focus on finding defects, while traditional game-playing agents focus on maximizing game scores. The synthetic agent uses test goals generated from game scenarios, and these goals are further modified to examine the effects of unintended game transitions. The humanlike agent uses test goals extracted by our proposed multiple greedy-policy inverse reinforcement learning (MGP-IRL) algorithm from tester trajectories. MGP-IRL captures multiple policies executed by human testers. We use our agents to produce test sequences, and run the game with these sequences. At each run, we use an automated test oracle to check for bugs. We analyze the proposed method in two parts-we compare the success of humanlike and synthetic agents in bug finding, and we evaluate the similarity between humanlike agents and human testers. We collected 427 trajectories from human testers using the General Video Game Artificial Intelligence (GVG-AI) framework and created three games with 12 levels that contain 45 bugs. Our experiments reveal that humanlike and synthetic agents compete with human testers' bug finding performances. Moreover, we show that MGP-IRL increases the humanlikeness of agents while improving the bug finding performance.
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.
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?
In the citing paper
“The sequence-based approach was previously used in automated video game testing agents [8] and was found more practical than non-sequence-based approaches.”
From Playtesting: What is Beyond Personas (2023) · cites this paper as [8]
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
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
A Survey of Monte Carlo Tree Search Methods
Browne, C. B., Powley, E., Whitehouse, D., Lucas, S. M., Cowling, P. I., Rohlfshagen, P., Tavener, S., Perez, D., Samothrakis, S., & Colton, S. (2012) · IEEE Transactions on Computational Intelligence and AI in Games · doi:10.1109/tciaig.2012.2186810 · Cited by 2,970 · cited 2×
“MCTS [20] is a search method that iteratively expands the search tree in the preferred direction.”
BackgroundMethod(2000) · doi:10.2460/ajvr.67.2.323 · Cited by 1,621
Human-Like Playtesting with Deep Learning
Gudmundsson, S. F., Eisen, P., Poromaa, E., Nodet, A., Purmonen, S., Kozakowski, B., Meurling, R., & Cao, L. (2018) · 2018 IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2018.8490442 · Cited by 90 · cited 2×
“Humanlike agents are better suited to analyze the difficulty of the game [10], can become genuine opponents [11],”
BackgroundMethod(2017) · doi:10.1145/3130859.3131439 · Cited by 56 · cited 5×
“[8] to explore the states of a point-and-click adventure game.”
BackgroundMethodInfluentialCombining Gameplay Data with Monte Carlo Tree Search to Emulate Human Play
Devlin, S., Anspoka, A., Sephton, N., Cowling, P., & Rollason, J. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v12i1.12858 · Cited by 28 · cited 1×
“Additionally, humanlike agents are used in games such as Unreal Tournament [11], Super Mario [38], Catan [39], GVG-AI [40], Spades [41], and Candy Crush [10].”
Method
Research works printed but not linked: 37
- 10.1109/CIG.2015.7317942 · DOI
- 10.1016/j.entcom.2012.10.001 · DOI
- ziebart, 0, Maximum entropy inverse reinforcement learning, Proc 23rd AAAI Conf Artif Intell, 1433
- 10.1145/1015330.1015430 · DOI · Paper page
- 10.1109/CIG.2014.6932868 · DOI · Paper page
- šoši?, 2018, Inverse reinforcement learning via nonparametric spatio-temporal subgoal modeling, J Mach Learn Res, 19, 2777
- 10.1007/978-3-642-33486-3_10 · DOI · Paper page
- babe?-vroman, 0, Apprenticeship learning about multiple intentions, Proc 28th Int Conf Int Conf Mach Learn, 897
- khalifa, 0, Modifying MCTS for human-like general video game playing, Proc 25th Int Joint Conf Artif Intell, 2514
- tastan, 0, Learning policies for first person shooter games using inverse reinforcement learning, Proc 7th AAAI Conf Artif Intell Interact Digit Entertainment, 85
- 10.1109/TCIAIG.2014.2363042 · DOI
- adams, 2014, Fundamentals of Game Design
- 10.1017/CBO9780511809163 · DOI · Paper page
- 10.1007/978-3-319-07064-3_6 · DOI
- 10.5220/0006556403550362 · doi:10.5220/0006556403550362
- mnih, 2015, Human-level control through deep reinforcement learning, Nature, 518, 529, 10.1038/nature14236 · DOI · Paper page
- 10.1109/CIG.2015.7317937 · DOI
- 10.7603/s40601-013-0010-4 · doi:10.7603/s40601-013-0010-4
- 10.1109/CIG.2018.8490417 · DOI
- 10.1145/3239235.3268923 · DOI
- 10.1109/MODELS.2015.7338274 · doi:10.1109/models.2015.7338274
- 10.1109/CIG.2016.7860448 · DOI
- 10.1109/CyberC.2010.54 · doi:10.1109/cyberc.2010.54
- 10.1016/j.entcom.2016.08.002 · doi:10.1016/j.entcom.2016.08.002
- 10.1109/32.6191 · DOI · Paper page
- 10.1007/s10664-018-9627-4 · DOI
- 10.1145/2700529 · DOI
- 10.1109/CIG.2008.5035667 · DOI · Paper page
- 10.2200/S00564ED1V01Y201311AIM024 · doi:10.2200/s00564ed1v01y201311aim024
- 10.1145/1822348.1822363 · DOI
- 10.1109/TG.2019.2901021 · DOI · Paper page
- 10.1145/3235765.3235790 · DOI
- sutton, 2018, Reinforcement Learning An Introduction
- 10.1109/ICCV.2017.399 · DOI · Paper page
- 10.1109/CEC.2018.8477829 · DOI
- 10.1016/bs.adcom.2015.05.003 · DOI
- 10.1109/TCIAIG.2014.2352795 · DOI · Paper page
Cited by
Predicting Game Difficulty and Churn Without Players
Roohi, S., Relas, A., Takatalo, J., Heiskanen, H., & Hämäläinen, P. (2020) · Proceedings of the Annual Symposium on Computer-Human Interaction in Play · doi:10.1145/3410404.3414235 · Cited by 34
Playtesting: What is Beyond Personas
Ariyurek, S., Surer, E., & Betin-Can, A. (2023) · IEEE Transactions on Games · doi:10.1109/tg.2022.3165882 · Cited by 7
“Lastly, though we promoted APF to find distinct paths, APF can benefit game tester agents [8] since increasing the coverage of tests is crucial in testing, and APF increases coverage by finding distinct paths.”
BackgroundMethodSelf-citation"Covertly Using" Generative AI in China's Game Industry
Guo, N., & Wen, W. (2025) · DiGRA Digital Library · doi:10.26503/dl.v2025i2.2453
Metadata
- Authors
- Ariyurek, S., Betin-Can, A., & Surer, E.
- Venue
- IEEE Transactions on Games
- Published
- 2021-03
- Volume
- 13
- Issue
- 1
- Pages
- 50-67
- ISSN
- 2475-1502
- 2475-1510
- Cited by
- 66
- References
- 6
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: Automated Video Game Testing Using Synthetic and Humanlike Agents. https://app.cochat.ai/papers/10.1109/tg.2019.2947597
- The paper
- Ariyurek, S., Betin-Can, A., & Surer, E. (2021). Automated Video Game Testing Using Synthetic and Humanlike Agents. IEEE Transactions on Games. https://doi.org/10.1109/tg.2019.2947597
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.