Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2402.13582 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929250640068608 |
|---|---|
| author | Yanggong, Yifan Pan, Hao Wang, Lei |
| author_facet | Yanggong, Yifan Pan, Hao Wang, Lei |
| contents | Games are a simplified model of reality and often serve as a favored platform for Artificial Intelligence (AI) research. Much of the research is concerned with game-playing agents and their decision making processes. The game of Guandan (literally, "throwing eggs") is a challenging game where even professional human players struggle to make the right decision at times. In this paper we propose a framework named GuanZero for AI agents to master this game using Monte-Carlo methods and deep neural networks. The main contribution of this paper is about regulating agents' behavior through a carefully designed neural network encoding scheme. We then demonstrate the effectiveness of the proposed framework by comparing it with state-of-the-art approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13582 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulating Yanggong, Yifan Pan, Hao Wang, Lei Artificial Intelligence Machine Learning Games are a simplified model of reality and often serve as a favored platform for Artificial Intelligence (AI) research. Much of the research is concerned with game-playing agents and their decision making processes. The game of Guandan (literally, "throwing eggs") is a challenging game where even professional human players struggle to make the right decision at times. In this paper we propose a framework named GuanZero for AI agents to master this game using Monte-Carlo methods and deep neural networks. The main contribution of this paper is about regulating agents' behavior through a carefully designed neural network encoding scheme. We then demonstrate the effectiveness of the proposed framework by comparing it with state-of-the-art approaches. |
| title | Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulating |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.13582 |