DanZero+: Dominating the GuanDan Game through Reinforcement Learning
- URL: http://arxiv.org/abs/2312.02561v1
- Date: Tue, 5 Dec 2023 08:07:32 GMT
- Title: DanZero+: Dominating the GuanDan Game through Reinforcement Learning
- Authors: Youpeng Zhao and Yudong Lu and Jian Zhao and Wengang Zhou and Houqiang
Li
- Abstract summary: We develop an AI program for an exceptionally complex and popular card game called GuanDan.
We first put forward an AI program named DanZero for this game.
In order to further enhance the AI's capabilities, we apply policy-based reinforcement learning algorithm to GuanDan.
- Score: 95.90682269990705
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The utilization of artificial intelligence (AI) in card games has been a
well-explored subject within AI research for an extensive period. Recent
advancements have propelled AI programs to showcase expertise in intricate card
games such as Mahjong, DouDizhu, and Texas Hold'em. In this work, we aim to
develop an AI program for an exceptionally complex and popular card game called
GuanDan. This game involves four players engaging in both competitive and
cooperative play throughout a long process to upgrade their level, posing great
challenges for AI due to its expansive state and action space, long episode
length, and complex rules. Employing reinforcement learning techniques,
specifically Deep Monte Carlo (DMC), and a distributed training framework, we
first put forward an AI program named DanZero for this game. Evaluation against
baseline AI programs based on heuristic rules highlights the outstanding
performance of our bot. Besides, in order to further enhance the AI's
capabilities, we apply policy-based reinforcement learning algorithm to
GuanDan. To address the challenges arising from the huge action space, which
will significantly impact the performance of policy-based algorithms, we adopt
the pre-trained model to facilitate the training process and the achieved AI
program manages to achieve a superior performance.
Related papers
- You Have Thirteen Hours in Which to Solve the Labyrinth: Enhancing AI Game Masters with Function Calling [35.721053667746716]
This paper presents a novel approach to enhance AI game masters by leveraging function calling in the context of the table-top role-playing game "Jim Henson's Labyrinth: The Adventure Game"
Our methodology involves integrating game-specific controls through functions, which we show improves the narrative quality and state update consistency of the AI game master.
arXiv Detail & Related papers (2024-09-11T02:03:51Z) - AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding [6.177038245239759]
This paper modifies the Deep Monte Carlo algorithm framework by using reinforcement learning to obtain a neural network that simultaneously estimates win rates and expectations.
The modified algorithm enables the AI to perform the full range of tasks in the Doudizhu game, including bidding and cardplay.
arXiv Detail & Related papers (2024-07-14T17:32:36Z) - Reinforcement Learning for High-Level Strategic Control in Tower Defense Games [47.618236610219554]
In strategy games, one of the most important aspects of game design is maintaining a sense of challenge for players.
We propose an automated approach that combines traditional scripted methods with reinforcement learning.
Results show that combining a learned approach, such as reinforcement learning, with a scripted AI produces a higher-performing and more robust agent than using only AI.
arXiv Detail & Related papers (2024-06-12T08:06:31Z) - Exploration with Principles for Diverse AI Supervision [88.61687950039662]
Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI.
While this generative AI approach has produced impressive results, it heavily leans on human supervision.
This strong reliance on human oversight poses a significant hurdle to the advancement of AI innovation.
We propose a novel paradigm termed Exploratory AI (EAI) aimed at autonomously generating high-quality training data.
arXiv Detail & Related papers (2023-10-13T07:03:39Z) - DanZero: Mastering GuanDan Game with Reinforcement Learning [121.93690719186412]
Card game AI has always been a hot topic in the research of artificial intelligence.
In this paper, we are devoted to developing an AI program for a more complex card game, GuanDan.
We propose the first AI program DanZero for GuanDan using reinforcement learning technique.
arXiv Detail & Related papers (2022-10-31T06:29:08Z) - Mastering the Game of No-Press Diplomacy via Human-Regularized
Reinforcement Learning and Planning [95.78031053296513]
No-press Diplomacy is a complex strategy game involving both cooperation and competition.
We introduce a planning algorithm we call DiL-piKL that regularizes a reward-maximizing policy toward a human imitation-learned policy.
We show that DiL-piKL can be extended into a self-play reinforcement learning algorithm we call RL-DiL-piKL.
arXiv Detail & Related papers (2022-10-11T14:47:35Z) - AI in Games: Techniques, Challenges and Opportunities [40.86375378643978]
Various game AI systems (AIs) have been developed such as Libratus, OpenAI Five and AlphaStar, beating professional human players.
In this paper, we survey recent successful game AIs, covering board game AIs, card game AIs, first-person shooting game AIs and real time strategy game AIs.
arXiv Detail & Related papers (2021-11-15T09:35:53Z) - ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep
Reinforcement Learning [2.7178968279054936]
We study Gongzhu, a trick-taking game analogous to, but slightly simpler than contract bridge.
We train a strong Gongzhu AI ScrofaZero from textittabula rasa by deep reinforcement learning.
We introduce new techniques for imperfect information game including stratified sampling, importance weighting, integral over equivalent class, Bayesian inference, etc.
arXiv Detail & Related papers (2021-02-15T12:01:44Z) - Suphx: Mastering Mahjong with Deep Reinforcement Learning [114.68233321904623]
We design an AI for Mahjong, named Suphx, based on deep reinforcement learning with some newly introduced techniques.
Suphx has demonstrated stronger performance than most top human players in terms of stable rank.
This is the first time that a computer program outperforms most top human players in Mahjong.
arXiv Detail & Related papers (2020-03-30T16:18:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.