Improving the Efficiency of Deep Reinforcement Learning in NetHack Using VAE and Proposing Additional Rewards
International Journal of Computer Games Technology · 2026-01 · 2026 (1)
DOI: 10.1155/ijcg/9867761 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Games Technology, online erschienen am 07.07.2026. Verfasst von Yasuhiro Onuki und 3 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.
Abstract (Originalsprache)
Deep reinforcement learning (DRL) has been widely used in agent research across various video games, demonstrating its effectiveness. Recently, there has been increasing interest in DRL research in complex environments such as Roguelike games. Among them, the game NetHack has gained research attention. In this study, we aim to train a DRL agent for efficient learning with reduced training costs using the NetHack Learning Environment (NLE). A variational autoencoder (VAE) can efficiently transform input states into latent representations. Therefore, we propose a method utilizing VAE, considering it as a potentially efficient DRL model. Additionally, because the rewards provided by NLE are sparse, we train a DRL agent with additional rewards. As a result, we find that providing additional rewards to the agent is effective for tackling NLE, where the reward space is sparse. Furthermore, our results suggest that directly using the latent representation of the VAE as input to the DRL model can be effective.
Förderung
- Japan Society for the Promotion of Science
Zitieren
APA
Onuki, Y., Tahara, Y., Ohsuga, A., & Sei, Y. (2026). Improving the Efficiency of Deep Reinforcement Learning in NetHack Using VAE and Proposing Additional Rewards. International Journal of Computer Games Technology, 2026(1). https://doi.org/10.1155/ijcg/9867761
Vancouver
Onuki Y, Tahara Y, Ohsuga A, Sei Y. Improving the Efficiency of Deep Reinforcement Learning in NetHack Using VAE and Proposing Additional Rewards. International Journal of Computer Games Technology. 2026;2026(1). doi:10.1155/ijcg/9867761
BibTeX
@article{Onuki2026,
author = {Onuki, Yasuhiro and Tahara, Yasuyuki and Ohsuga, Akihiko and Sei, Yuichi},
title = {Improving the Efficiency of Deep Reinforcement Learning in NetHack Using VAE and Proposing Additional Rewards},
journal = {International Journal of Computer Games Technology},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/ijcg/9867761}
}
EUVIMED