Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2203.16406 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910345765847040 |
|---|---|
| author | Yang, Guan Liu, Minghuan Hong, Weijun Zhang, Weinan Fang, Fei Zeng, Guangjun Lin, Yue |
| author_facet | Yang, Guan Liu, Minghuan Hong, Weijun Zhang, Weinan Fang, Fei Zeng, Guangjun Lin, Yue |
| contents | As a challenging multi-player card game, DouDizhu has recently drawn much attention for analyzing competition and collaboration in imperfect-information games. In this paper, we propose PerfectDou, a state-of-the-art DouDizhu AI system that dominates the game, in an actor-critic framework with a proposed technique named perfect information distillation. In detail, we adopt a perfect-training-imperfect-execution framework that allows the agents to utilize the global information to guide the training of the policies as if it is a perfect information game and the trained policies can be used to play the imperfect information game during the actual gameplay. To this end, we characterize card and game features for DouDizhu to represent the perfect and imperfect information. To train our system, we adopt proximal policy optimization with generalized advantage estimation in a parallel training paradigm. In experiments we show how and why PerfectDou beats all existing AI programs, and achieves state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2203_16406 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | PerfectDou: Dominating DouDizhu with Perfect Information Distillation Yang, Guan Liu, Minghuan Hong, Weijun Zhang, Weinan Fang, Fei Zeng, Guangjun Lin, Yue Artificial Intelligence Computer Science and Game Theory Machine Learning As a challenging multi-player card game, DouDizhu has recently drawn much attention for analyzing competition and collaboration in imperfect-information games. In this paper, we propose PerfectDou, a state-of-the-art DouDizhu AI system that dominates the game, in an actor-critic framework with a proposed technique named perfect information distillation. In detail, we adopt a perfect-training-imperfect-execution framework that allows the agents to utilize the global information to guide the training of the policies as if it is a perfect information game and the trained policies can be used to play the imperfect information game during the actual gameplay. To this end, we characterize card and game features for DouDizhu to represent the perfect and imperfect information. To train our system, we adopt proximal policy optimization with generalized advantage estimation in a parallel training paradigm. In experiments we show how and why PerfectDou beats all existing AI programs, and achieves state-of-the-art performance. |
| title | PerfectDou: Dominating DouDizhu with Perfect Information Distillation |
| topic | Artificial Intelligence Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2203.16406 |