检索结果-内蒙古大学图书馆

30th Chinese Control and Decision Conference (CCDC)

作者： Fu, Yao Li, Shuqin Qi, Yanan Beijing Informat Sci Technol Univ Beijing 100085 Peoples R China Sensing & Computat Intelligence Joint Lab Beijing 100085 Peoples R China

ISBN: (纸本)9781538612446

Aiming at the great difficulty of branches of Amazon, this paper presents a staged uct search algorithm based on Amazon chess. First of all, generate 100,000 simulation chess game data through self-play game, use K -means algorithm to determine the Amazon chess game three stages. Then, We give the uct search algorithm of the three stages of the start, the middle and the ending, so that the program call achieve a good balance between the search effect and the calculation delay, and get a good effect in the experiment.

关键词： Computer game Amazon game stage self-play game uct algorithm

来源：评论

学校读者我要写书评

暂无评论

Amazon game system design and realization based on staged uct algorithm

Amazon game system design and realization based on staged UC...

引用

第30届中国控制与决策会议

作者： Yao Fu Shuqin Li Yanan Qi Beijing Information Science & Technology University

Aiming at the great difficulty of branches of Amazon, this paper presents a staged uct search algorithm based on Amazon chess. First of all, generate 100,000 simulation chess game data through self-play game, use K-means algorithm to determine the Amazon chess game three stages. Then, we give the uct search algorithm of the three stages of the start, the middle and the ending, so that the program can achieve a good balance between the search effect and the calculation delay, and get a good effect in the experiment.

关键词： Computer game Amazon game stage self-play game uct algorithm

来源：评论

学校读者我要写书评

暂无评论

Research on Parallel Optimization of uct algorithm for NoGo Computer Game 29

Research on Parallel Optimization of UCT Algorithm for NoGo ...

引用

第29届中国控制与决策会议

作者： Zhang Ziyang Sun Yuxia College of Aerospace Engineering Shenyang Aerospace University Engineering Training Center Shenyang Aerospace University

ISBN: (纸本)9781509046584

The theoretical system and evaluation methods of NoGo is not mature for it is been proposed in recent *** uct algorithm has become a popular approach for NoGo *** uct algorithm based on Monte-Carlo Tree Search only runs on a single thread,which does not make full use of multi-core CPU *** this paper,a multi-thread parallel optimization method of uct algorithm is put *** experimental results show that the parallel optimized uct algorithm enhances researching efficiency for NoGo,and makes the decisions of the best move for NoGo faster and more ***,it also increases the skill of NoGo game.

关键词： NoGo uct algorithm Parallel Optimization Computer Game

来源：评论

学校读者我要写书评

暂无评论

Amazon Chess Based on uct-PVS Hybrid algorithm 33

Amazon Chess Based on UCT-PVS Hybrid Algorithm

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Li, Zhuoxuan Ning, Chenhui Cao, Jinde Li, Zhengyu Southeast Univ Sch Math Nanjing 210096 Peoples R China Yonsei Univ Yonsei Frontier Lab Seoul 03722 South Korea Big Fish Tournaments Beijing Network Technol Co L Beijing 100029 Peoples R China

ISBN: (纸本)9781665440899

Amazon Chess is a game with complexity between Go and Chinese Chess. Its complexity is mainly due to its extremely large branching factor, which makes it difficult to reach a high depth in the search process. This paper adopts the hybrid search algorithm combines with Upper Confidence bounds Trees search algorithm (uct) and Principal Variation Search (PVS), which is called uct-PVS hybrid search algorithm. The uct algorithm is used at the opening stage to enable the game player to obtain a more advantageous *** PVS combines with Historical Heuristics and Transposition Table, by reducing the pruning window, the pruning efficiency is effectively increased and greatly improves the search depth. The Amazon Chess software is developed by using this technology and is effectively improved its game level.

关键词： Amazon Chess uct algorithm PVS algorithm uct-PVS hybrid algorithm Transposition Table Historical Heuristics

来源：评论

学校读者我要写书评

暂无评论

uct algorithm in Amazons Human-computer Games

UCT Algorithm in Amazons Human-computer Games

引用

26th Chinese Control and Decision Conference (CCDC)

作者： Li, Xiali Hou, Liang Wu, Licheng MINZU Univ China Sch Informat Engn Beijing 100081 Peoples R China

ISBN: (纸本)9781479937066

The main difficulty of Amazons games is the huge branch factor. Traditional NegaMax Search and Alpha-Beta Search can only search a few layers and can't improve the games effectively. Monte-Carlo algorithm can improve the games but it needs a huge amount of computing. This paper studies applying uct algorithm to the Amazons games to overcome this problem in order to balance the search efficiency and computing load. In uct mini-max tree search, the algorithm select tree node according to the node's UCB (Upper Confidence Bound) value. Then evaluate the selected node and return the optimal moves. Using C++ programming language, we implemented Amazons human-computer games software. The experiments show that uct algorithm can implement the search work in Amazons human-computer games and get satisfactory search efficiency.

关键词： Artificial Intelligence Computer Games Amazons uct algorithm Monte-Carlo

来源：评论

学校读者我要写书评

暂无评论

Neural-augmented two-stage Monte Carlo tree search with over-sampling for protein folding in HP Model

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2022年第5期17卷 685-694页

作者： Deng, Hangyu Yuan, Xin Tian, Yanling Hu, Jinglu Waseda Univ Grad Sch Informat Prod & Syst 2-7 Hibikino Kitakyushu Fukuoka 8080135 Japan

This paper proposes a novel Monte Carlo tree search (MCTS) algorithm to solve the protein folding problem in HP model. There are two main challenges. First, the problem is proved to be NP-complete. The solution space is large and it is hard to find a good solution via a search algorithm without prior knowledge of the HP model. We tackle this challenge by formulating the problem as a deterministic Markov decision process (MDP) and solve it in an AlphaZero's manner. The difference is that we design a MCTS algorithm with two stages: neural exploitation stage and random exploration stage. In the first stage, the search algorithm utilizes the knowledge from previous experience by evaluating the states with a trained neural network, while in the second stage, the states are evaluated by fast and random rollouts. It effectively reduces the number of neural inferences and computational cost. The second challenge is that the evaluation of typical MCTS cannot preserve the correct preference over the actions in our task. To address this challenge, we propose an over-sampling mechanism that encourages the agent to search more on those actions with high rollout values. The proposed method is tested and compared in a series of experiments. Experimental results have confirmed the effectiveness of the proposed method empirically. Besides, we also visualize the obtained the best conformations and verify the proposed technical designs through an ablation study. (c) 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

关键词： protein folding problem HP model reinforcement learning Monte Carlo tree search uct algorithm

来源：评论

学校读者我要写书评

暂无评论

Amazon Chess Based on uct-PVS Hybrid algorithm

Amazon Chess Based on UCT-PVS Hybrid Algorithm

引用

第33届中国控制与决策会议

作者： Zhuoxuan Li Chenhui Ning Jinde Cao Zhengyu Li School of Mathematics Southeast University Yonsei Frontier Lab Yonsei University

Amazon Chess is a game with complexity between Go and Chinese *** complexity is mainly due to its extremely large branching factor,which makes it difficult to reach a high depth in the search *** paper adopts the hybrid search algorithm combines with Upper Confidence bounds Trees search algorithm（uct） and Principal Variation Search（PVS）,which is called uct-PVS hybrid search *** uct algorithm is used at the opening stage to enable the game player to obtain a more advantageous *** PVS combines with Historical Heuristics and Transposition Table,by reducing the pruning window,the pruning efficiency is effectively increased and greatly i mproves the search *** Amazon Chess software is developed by using this technology and is effectively improved its game level.

关键词： Amazon Chess uct algorithm PVS algorithm uct-PVS hybrid algorithm Transposition Table Historical Heuristics

来源：评论

学校读者我要写书评

暂无评论

Combining M-MCTS and Deep Reinforcement Learning for General Game Playing 1

引用

3rd International Conference on Distributed Artificial Intelligence, DAI 2021

作者： Liang, Sili Jiang, Guifei Zhang, Yuzhi College of Software Nankai University Tianjin300350 China

ISBN: (数字)9783030946623

ISBN: (纸本)9783030946616

As one of the main research areas in AI, General Game Playing (GGP) is concerned with creating intelligent agents that can play more than one game based on game rules without human intervention. Most recent work has successfully applied deep reinforcement learning to GGP. This paper continues this line of work by integrating the Memory-Augmented Monte Carlo Tree Search algorithm (M-MCTS) with deep reinforcement learning for General Game Playing. We first extend M-MCTS from playing the single game Go to multiple concurrent games so as to cater to the domain of GGP. Then inspired by Goldwaser and Thielscher (2020), we combine the extension with deep reinforcement learning for building a general game player. Finally, we have tested this player on several games compared with the benchmark uct player, and the experimental results have confirmed the feasibility of applying M-MCTS and deep reinforcement learning to GGP. © 2022, Springer Nature Switzerland AG.

关键词： Deep reinforcement learning General game player General Game Playing Memory-Augmented Monte Carlo Tree Search uct algorithm

来源：评论

学校读者我要写书评

暂无评论

uct algorithm in Amazons Human-computer Games

UCT Algorithm in Amazons Human-computer Games

引用

第26届中国控制与决策会议

作者： Xiali Li Liang Hou Licheng Wu School of Information Engineering MINZU University of China

The main difficulty of Amazons games is the huge branch factor. Traditional NegaMax Search and Alpha-Beta Search can only search a few layers and can't improve the games effectively. Monte-Carlo algorithm can improve the games but it needs a huge amount of computing. This paper studies applying uct algorithm to the Amazons games to overcome this problem in order to balance the search efficiency and computing load. In uct mini-max tree search, the algorithm select tree node according to the node's UCB(Upper Confidence Bound) *** evaluate the selected node and return the optimal moves. Using C++ programming language, we implemented Amazons human-computer games software. The experiments show that uct algorithm can implement the search work in Amazons human-computer games and get satisfactory search efficiency.

关键词： Artificial Intelligence Computer Games Amazons uct algorithm Monte-Carlo

来源：评论

学校读者我要写书评

暂无评论

Research on Search algorithm in Surakarta Chess Game System

International Core Journal of Engineering

引用

International Core Journal of Engineering 2023年第7期9卷 286-293页

作者： Tao Zhang Yefeng Jiang Bowen Li

This paper introduces Surakarta, an important branch in the field of computer games, and discusses two search algorithms used in this game: Alpha-Beta pruning algorithm and uct algorithm. The search algorithm plays a central role in the game system and affects the performance and efficiency of the system. Alpha-Beta pruning algorithm is an optimized and improved maxima-minimum algorithm, which reduces unnecessary search branches and improves search efficiency through pruning principles. The uct algorithm is a game tree search algorithm based on the Monte Carlo method, which estimates the true value of the action through random simulation and tree building and expansion, and adjusts the strategy to the best priority strategy. The application of these two algorithms in the Surakarta chess game system can improve the performance and accuracy of computer games. Through the research and application of Surakarta chess, it can not only promote the development of artificial intelligence in chess games, but also provide enlightenment for problem solving in other fields.

关键词： Surakarta Chess Alpha-Beta algorithm uct algorithm Monte Carlo algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：