Playing the Snake Game with Reinforcement Learning
Cambridge Explorations in Arts and Sciences · 2023
DOI: 10.61603/ceas.v1i1.13 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cambridge Explorations in Arts and Sciences, 2023. Verfasst von Pan Yuhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).
Abstract (Originalsprache)
When it is necessary to make several decisions to solve a problem, reinforcement learning works well. In this project, we demonstrate the outcomes of playing with snakes using a Deep Q-Network (DQN). Unfortunately, DQN has a tendency to overfit, which results in a deterioration in terms of scores that are subpar after numerous training sessions. To solve this issue, we enhanced the reward setting and provided the snake with more information about its surroundings in order to raise our score and prevent some overfitting issues. Also, we went through the differences between DQN and conventional evolutionary algorithms as well as possible avenues for DQN optimization.
Zitieren
APA
Yuhang, P., Yiqi, S., Qianli, M., Bowen, G., Junyi, D., & Zijun, T. (2023). Playing the Snake Game with Reinforcement Learning. Cambridge Explorations in Arts and Sciences. https://doi.org/10.61603/ceas.v1i1.13
Vancouver
Yuhang P, Yiqi S, Qianli M, Bowen G, Junyi D, Zijun T. Playing the Snake Game with Reinforcement Learning. Cambridge Explorations in Arts and Sciences. 2023. doi:10.61603/ceas.v1i1.13
BibTeX
@article{Yuhang2023,
author = {Yuhang, Pan and Yiqi, Song and Qianli, Ma and Bowen, Gu and Junyi, Dong and Zijun, Tang},
title = {Playing the Snake Game with Reinforcement Learning},
journal = {Cambridge Explorations in Arts and Sciences},
year = {2023},
doi = {10.61603/ceas.v1i1.13}
}
EUVIMED