Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning

Löwe, Mathias; Villareale, Jennifer; Freed, Evan; Sladek, Aleksanteri; Zhu, Jichen; Risi, Sebastian

doi:10.1145/3472538.3472540

Cited by 4 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[25] dataset and includes 40 million drawings across 345 categories (i.e., 345 supported codewords) of example sketches. For more detailed information on the NN's architecture, see [43].…”

Section: Neuralmentioning

confidence: 99%

See 1 more Smart Citation

"I Want To See How Smart This AI Really Is": Player Mental Model Development of an Adversarial AI Player

Villareale

Harteveld

Zhu

2022

Proc. ACM Hum.-Comput. Interact.

Self Cite

View full text Add to dashboard Cite

Understanding players' mental models are crucial for game designers who wish to successfully integrate player-AI interactions into their game. However, game designers face the difficult challenge of anticipating how players model these AI agents during gameplay and how they may change their mental models with experience. In this work, we conduct a qualitative study to examine how a pair of players develop mental models of an adversarial AI player during gameplay in the multiplayer drawing game iNNk. We conducted ten gameplay sessions in which two players (n = 20, 10 pairs) worked together to defeat an AI player. As a result of our analysis, we uncovered two dominant dimensions that describe players' mental model development (i.e., focus and style). The first dimension describes the focus of development which refers to what players pay attention to for the development of their mental model (i.e., top-down vs. bottom-up focus). The second dimension describes the differences in the style of development, which refers to how players integrate new information into their mental model (i.e., systematic vs. reactive style). In our preliminary framework, we further note how players process a change when a discrepancy occurs, which we observed occur through comparisons (i.e., compare to other systems, compare to gameplay, compare to self). We offer these results as a preliminary framework for player mental model development to help game designers anticipate how different players may model adversarial AI players during gameplay.

show abstract

“…[25] dataset and includes 40 million drawings across 345 categories (i.e., 345 supported codewords) of example sketches. For more detailed information on the NN's architecture, see [43].…”

Section: Neuralmentioning

confidence: 99%

“…Constructing such a system or adapting an NN to account for this can be challenging [43]. Game designers could also detect mental model development explicitly by asking players to describe the state of their mental model through in-game prompts, which is a common approach to facilitate reflection in learning games [65].…”

Section: Detecting Mental Models Of Aimentioning

confidence: 99%