Academic Journal of Computing & Information Science, 2024, 7(11); doi: 10.25236/AJCIS.2024.071114.
Shi-Tao Chang
Jericho Senior High School, 99 Cedar Swamp Rd, Jericho, NY, USA, 11753
Artificial Intelligence (AI) has the potential to outperform humans in even the most strategic, creativity-based games. Previous work that incorporated AI players for such games—like Dixit—involving text generation has explored hint generation but never the implementation and thorough application of said generated text. To address these limitations, we built upon existing datasets of hints and established a game interface upon which we used CLIP by Open AI. We also use Jupyter Notebook and Conda to recognize images, convert them to vectors, compare the cosine similarity, and select the optimal hint thereafter for use in gameplay. We find that the AI player is successful in a significant percentage of the rounds in picking optimal hints. Future studies may address the generation of new hints to expand the dataset of hints from which the AI player can draw.
Artificial Intelligence, AI players, Dixit, text-generation, hint selection, game interface, CLIP, OpenAI, cosine similarity
Shi-Tao Chang. Dixit AI: An OpenAI Clip-based Hint Selection Player. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 11: 102-108. https://doi.org/10.25236/AJCIS.2024.071114.
[1] Gupta, A., Anpalagan, A., Guan, L. and Khwaja, A. S. (2021). Deep learning for object detection and scene perception in self-driving cars: Survey, challenges, and open issues. Array, 10, 100057. https://doi.org/10.1016/j.array.2021.100057
[2] Bohr, A. and Memarzadeh, K. (2020). The rise of artificial intelligence in healthcare applications. Elsevier. https://doi.org/10.1016/b978-0-12-818438-7.00002-2
[3] Xue, Z., Xu, C. and Xu, X. (2023, July). Application of ChatGPT in natural disaster prevention and reduction. https://doi.org/10.1016/j.nhres.2023.07.005
[4] Vatsakis, D., Blom, P. M. and Spronck, P. (2022). An Internet-assisted Dixit-playing AI [Paper presentation]. 17th International Conference on the Foundations of Digital Games. https://doi.org/ 10.1145/3555858.3555863
[5] Cherti, M., Beaumont, R., Wightman, R., Wortsman, M., Ilharco, G., Gordon, C., Schuhmann, C., Schmidt, L. and Jitsev, J. (2024, July 13). Reproducible scaling laws for contrastive language-image learning. arXiv.org. https://arxiv.org/abs/2212.07143