Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913376916996096 |
|---|---|
| author | Zhang, Chen He, Qiang Yuan, Zhou Liu, Elvis S. Wang, Hong Zhao, Jian Wang, Yang |
| author_facet | Zhang, Chen He, Qiang Yuan, Zhou Liu, Elvis S. Wang, Hong Zhao, Jian Wang, Yang |
| contents | Deep Reinforcement Learning (DRL) agents have demonstrated impressive success in a wide range of game genres. However, existing research primarily focuses on optimizing DRL competence rather than addressing the challenge of prolonged player interaction. In this paper, we propose a practical DRL agent system for fighting games named Shūkai, which has been successfully deployed to Naruto Mobile, a popular fighting game with over 100 million registered users. Shūkai quantifies the state to enhance generalizability, introducing Heterogeneous League Training (HELT) to achieve balanced competence, generalizability, and training efficiency. Furthermore, Shūkai implements specific rewards to align the agent's behavior with human expectations. Shūkai's ability to generalize is demonstrated by its consistent competence across all characters, even though it was trained on only 13% of them. Additionally, HELT exhibits a remarkable 22% improvement in sample efficiency. Shūkai serves as a valuable training partner for players in Naruto Mobile, enabling them to enhance their abilities and skills. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01103 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment Zhang, Chen He, Qiang Yuan, Zhou Liu, Elvis S. Wang, Hong Zhao, Jian Wang, Yang Artificial Intelligence Human-Computer Interaction Machine Learning Deep Reinforcement Learning (DRL) agents have demonstrated impressive success in a wide range of game genres. However, existing research primarily focuses on optimizing DRL competence rather than addressing the challenge of prolonged player interaction. In this paper, we propose a practical DRL agent system for fighting games named Shūkai, which has been successfully deployed to Naruto Mobile, a popular fighting game with over 100 million registered users. Shūkai quantifies the state to enhance generalizability, introducing Heterogeneous League Training (HELT) to achieve balanced competence, generalizability, and training efficiency. Furthermore, Shūkai implements specific rewards to align the agent's behavior with human expectations. Shūkai's ability to generalize is demonstrated by its consistent competence across all characters, even though it was trained on only 13% of them. Additionally, HELT exhibits a remarkable 22% improvement in sample efficiency. Shūkai serves as a valuable training partner for players in Naruto Mobile, enabling them to enhance their abilities and skills. |
| title | Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment |
| topic | Artificial Intelligence Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2406.01103 |