2019 IEEE Conference on Games (CoG) 2019
DOI: 10.1109/cig.2019.8848015
|View full text |Cite
|
Sign up to set email alerts
|

Fusing Level and Ruleset Features for Multimodal Learning of Gameplay Outcomes

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
8
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
3
2
2

Relationship

1
6

Authors

Journals

citations
Cited by 9 publications
(8 citation statements)
references
References 28 publications
0
8
0
Order By: Relevance
“…Moreover, experiments in using visualizations of e.g. powerup safety for these FPS level layouts showed that more accurate predictions for gameplay metrics could be achieved [39]. Including this input to the deep learning models of temporal or spatial qualities could also lead to higher accuracy in these harder prediction tasks.…”
Section: Discussionmentioning
confidence: 99%
See 2 more Smart Citations
“…Moreover, experiments in using visualizations of e.g. powerup safety for these FPS level layouts showed that more accurate predictions for gameplay metrics could be achieved [39]. Including this input to the deep learning models of temporal or spatial qualities could also lead to higher accuracy in these harder prediction tasks.…”
Section: Discussionmentioning
confidence: 99%
“…6). This is not surprising, as the predictions for kill ratio (which is used to calculate f ) mainly uses the class parameters [39] with limited impact from the level input. Interestingly, all best differentclass suggestions were with Soldier vs. Sniper (or vice versa); the hypothesis is that both classes are long-range and the range class parameter is a strong predictor of kill ratio.…”
Section: Experiments On Suggestion Generationmentioning
confidence: 99%
See 1 more Smart Citation
“…We are aware that bridging the approaches, expectations, and mindsets between technical and nontechnical AI explanations, is a tough task, and needs more research and discussions, not only in the XAI community, but also interdisciplinary collaborations from HCI [51,25,55,15,28], social sciences, and behavioral sciences [21,16,42,30]. Currently, based on our case study and literature research, we are proposing a detailed workflow that put both technical and non-technical AI stakeholders at the center, for high-stake decisions in AI's deployment in real life.…”
Section: Work In Progressmentioning
confidence: 99%
“…More recently, Li et al (2019) This work draws on convolutional neural networks (CNNs) to predict commentary for a particular frame of a gameplay video. CNNs have been employed to take an input snapshot of a game and predict player experience (Guzdial, Sturtevant, and Li 2016; Liao, Guzdial, and Riedl 2017), game balance (Liapis et al 2019), and the utility of particular game states (Stanescu et al 2016).…”
Section: Related Workmentioning
confidence: 99%