The article presents the path planning algorithm to be applied in the Chinese chess game, and uses multiple mobile robots to present the experimental scenario. Users play the Chinese chess game using the mouse on the ...The article presents the path planning algorithm to be applied in the Chinese chess game, and uses multiple mobile robots to present the experimental scenario. Users play the Chinese chess game using the mouse on the supervised computer. The supervised computer programs the motion paths using A＊ searching algorithm, and controls mobile robots moving on the grid based chessboard platform via wireless radio frequency （RF） interface. The A＊ searching algorithm solves shortest path problems of mobile robots from the start point to the target point, and avoids the obstacles on the chessboard platform. The supervised computer calculates the total time to play the game, and computes the residual time to play chess in the step for each player. The simulation results can fired out the shortest motion paths of the mobile robots （chesses） moving to target points from start points in the monitor, and decides the motion path to be existence or not. The eaten chess can moves to the assigned position, and uses the A＊ searching algorithm to program the motion path, too. Finally, the authors implement the simulation results on the chessboard platform using mobile robots. Users can play the Chinese chess game on the supervised computer according to the Chinese chess game rule, and play each step of the game in the assigned time. The supervised computer can suggests which player don＇t obey the rules of the game, and decides which player to be a winner. The scenario of the Chinese chess game feedback to the user interface using the image system.展开更多
The chess game provides a very rich experience in neighborhood types. The chess pieces have vertical, horizontal, diagonal, up/down or combined movements on one or many squares of the chess. These movements can associ...The chess game provides a very rich experience in neighborhood types. The chess pieces have vertical, horizontal, diagonal, up/down or combined movements on one or many squares of the chess. These movements can associate with neighborhoods. Our work aims to set a behavioral approximation between calculations carried out by means of traditional computation tools such as ordinary differential equations (ODEs) and the evolution of the value of the cells caused by the chess game moves. Our proposal is based on a grid. The cells’ value changes as time pass depending on both their neighborhood and an update rule. This framework succeeds in applying real data matching in the cases of the ODEs used in compartmental models of disease expansion, such as the well-known Susceptible-Infected Recovered (SIR) model and its derivatives, as well as in the case of population dynamics in competition for resources, depicted by the Lotke-Volterra model.展开更多
Since the promulgation and implementation of "Learning and Development Guide for Children Aged 3-6" for 10 years, teachers have deeply realized that games play an important role in the implementation of kind...Since the promulgation and implementation of "Learning and Development Guide for Children Aged 3-6" for 10 years, teachers have deeply realized that games play an important role in the implementation of kindergarten curriculum in the process of kindergarten curriculum reform, and gradually turned their attention to children and their game activities, paying attention to their behaviors, emotions and experiences in games. As an integral part of kindergarten education, regional game activities have become an important way for children to learn and develop. Then, how to observe children, record children, analyze childrens game behavior in regional games, and then support and guide childrens development has become a big problem in teachers professional growth. Therefore, under the guidance of the subject, our garden has reorganized the regional observation cases, carried out relevant training, conducted kindergarten-based teaching and research, reviewed teachers observation behaviors and records, identified the problems, clearly positioned them, and gradually adjusted them, so as to improve teachers game observation and record level, so as to support teachers to play a guiding role in childrens game activities.展开更多
China’s ethnic minorities have invented a variety of different chess games.For example, the Maonan ethnic group,living in Huanjiang county,Guangxi Zhuang Autonomous Region, has invented eight ways of playing chess,de...China’s ethnic minorities have invented a variety of different chess games.For example, the Maonan ethnic group,living in Huanjiang county,Guangxi Zhuang Autonomous Region, has invented eight ways of playing chess,despite a small population of about 100,000 people.展开更多
目前传统卷积网络在爱恩斯坦棋中的运用已颇显成效,但存在着训练速度慢,在浅层次的卷积中无法关注到全局信息的缺点,通过改进深度学习算法和使用GNN取代卷积神经网络(CNN),发现可以显著提升模型性能。研究方法包括将爱恩斯坦棋的棋盘和...目前传统卷积网络在爱恩斯坦棋中的运用已颇显成效,但存在着训练速度慢,在浅层次的卷积中无法关注到全局信息的缺点,通过改进深度学习算法和使用GNN取代卷积神经网络(CNN),发现可以显著提升模型性能。研究方法包括将爱恩斯坦棋的棋盘和移动规则表示为图结构,构建GNN以在较浅层次中捕捉局部与全局特征。同时结合蒙特卡洛树搜索(monte carlo tree search,MCTS),通过神经网络的策略头和价值头,提供行动决策和局势评估。实验中,将改进后的GNN算法与传统CNN算法在多轮自对弈中进行对比,结果显示,GNN在局势预测、策略控制及训练效率方面均优于CNN,随着训练次数的增加,该方法在效率提升方面表现出更显著的优势。GNN的应用提升了爱恩斯坦棋博弈模型的效率与策略能力,为进一步探索GNN在完美信息博弈中的潜在价值提供了理论支持和实践基础。展开更多
Game-tree search plays an important role in the field of Artificial Intelligence （AI）. In this paper, we characterize one parallel game-tree search workload in chess： the latest version of Crafty, a state of art pr...Game-tree search plays an important role in the field of Artificial Intelligence （AI）. In this paper, we characterize one parallel game-tree search workload in chess： the latest version of Crafty, a state of art program, on two Intel Xeon shared-memory multiprocessor systems. Our analysis shows that Crafty is latency-sensitive and the hash-table and dynamic tree splitting used in Crafty cause large scalability penalties. They consume 35%-50% of the running time on the 4-way system. Furthermore, Crafty is not bandwidth-limited.展开更多
针对蒙特卡洛树搜索算法(Monte Carlo tree search,MCTS)收敛速度过慢,且在博弈过程中关键节点会出现信息丢失等问题,以中国象棋为载体,构建适用于中国象棋博弈系统的策略价值网络,提出了一种基于统计数据的并行蒙特卡洛树搜索算法(para...针对蒙特卡洛树搜索算法(Monte Carlo tree search,MCTS)收敛速度过慢,且在博弈过程中关键节点会出现信息丢失等问题,以中国象棋为载体,构建适用于中国象棋博弈系统的策略价值网络,提出了一种基于统计数据的并行蒙特卡洛树搜索算法(parallel Monte Carlo tree search based on statistics,SPMCTS)。将并行化的重点设置在MCTS四个步骤中最耗时的扩展和模拟步骤,有效避免了算法执行过程中的等待时差。并且引入一组新统计数据,这些数据用于在MCTS的选择步骤中修改节点的选择策略,保证在进行节点选择时获取和利用更多的可用信息,缓解信息丢失对精度造成的影响。实验结果表明,与现有并行蒙特卡洛树算法相比,SPMCTS在搜索速度上加快了约34%,且在对弈实验中,博弈胜率也能保持在80%左右。验证了SPMCTS的有效性。展开更多
文摘The article presents the path planning algorithm to be applied in the Chinese chess game, and uses multiple mobile robots to present the experimental scenario. Users play the Chinese chess game using the mouse on the supervised computer. The supervised computer programs the motion paths using A＊ searching algorithm, and controls mobile robots moving on the grid based chessboard platform via wireless radio frequency （RF） interface. The A＊ searching algorithm solves shortest path problems of mobile robots from the start point to the target point, and avoids the obstacles on the chessboard platform. The supervised computer calculates the total time to play the game, and computes the residual time to play chess in the step for each player. The simulation results can fired out the shortest motion paths of the mobile robots （chesses） moving to target points from start points in the monitor, and decides the motion path to be existence or not. The eaten chess can moves to the assigned position, and uses the A＊ searching algorithm to program the motion path, too. Finally, the authors implement the simulation results on the chessboard platform using mobile robots. Users can play the Chinese chess game on the supervised computer according to the Chinese chess game rule, and play each step of the game in the assigned time. The supervised computer can suggests which player don＇t obey the rules of the game, and decides which player to be a winner. The scenario of the Chinese chess game feedback to the user interface using the image system.
文摘The chess game provides a very rich experience in neighborhood types. The chess pieces have vertical, horizontal, diagonal, up/down or combined movements on one or many squares of the chess. These movements can associate with neighborhoods. Our work aims to set a behavioral approximation between calculations carried out by means of traditional computation tools such as ordinary differential equations (ODEs) and the evolution of the value of the cells caused by the chess game moves. Our proposal is based on a grid. The cells’ value changes as time pass depending on both their neighborhood and an update rule. This framework succeeds in applying real data matching in the cases of the ODEs used in compartmental models of disease expansion, such as the well-known Susceptible-Infected Recovered (SIR) model and its derivatives, as well as in the case of population dynamics in competition for resources, depicted by the Lotke-Volterra model.
文摘Since the promulgation and implementation of "Learning and Development Guide for Children Aged 3-6" for 10 years, teachers have deeply realized that games play an important role in the implementation of kindergarten curriculum in the process of kindergarten curriculum reform, and gradually turned their attention to children and their game activities, paying attention to their behaviors, emotions and experiences in games. As an integral part of kindergarten education, regional game activities have become an important way for children to learn and develop. Then, how to observe children, record children, analyze childrens game behavior in regional games, and then support and guide childrens development has become a big problem in teachers professional growth. Therefore, under the guidance of the subject, our garden has reorganized the regional observation cases, carried out relevant training, conducted kindergarten-based teaching and research, reviewed teachers observation behaviors and records, identified the problems, clearly positioned them, and gradually adjusted them, so as to improve teachers game observation and record level, so as to support teachers to play a guiding role in childrens game activities.
文摘China’s ethnic minorities have invented a variety of different chess games.For example, the Maonan ethnic group,living in Huanjiang county,Guangxi Zhuang Autonomous Region, has invented eight ways of playing chess,despite a small population of about 100,000 people.
文摘目前传统卷积网络在爱恩斯坦棋中的运用已颇显成效,但存在着训练速度慢,在浅层次的卷积中无法关注到全局信息的缺点,通过改进深度学习算法和使用GNN取代卷积神经网络(CNN),发现可以显著提升模型性能。研究方法包括将爱恩斯坦棋的棋盘和移动规则表示为图结构,构建GNN以在较浅层次中捕捉局部与全局特征。同时结合蒙特卡洛树搜索(monte carlo tree search,MCTS),通过神经网络的策略头和价值头,提供行动决策和局势评估。实验中,将改进后的GNN算法与传统CNN算法在多轮自对弈中进行对比,结果显示,GNN在局势预测、策略控制及训练效率方面均优于CNN,随着训练次数的增加,该方法在效率提升方面表现出更显著的优势。GNN的应用提升了爱恩斯坦棋博弈模型的效率与策略能力,为进一步探索GNN在完美信息博弈中的潜在价值提供了理论支持和实践基础。
文摘Game-tree search plays an important role in the field of Artificial Intelligence （AI）. In this paper, we characterize one parallel game-tree search workload in chess： the latest version of Crafty, a state of art program, on two Intel Xeon shared-memory multiprocessor systems. Our analysis shows that Crafty is latency-sensitive and the hash-table and dynamic tree splitting used in Crafty cause large scalability penalties. They consume 35%-50% of the running time on the 4-way system. Furthermore, Crafty is not bandwidth-limited.
文摘针对蒙特卡洛树搜索算法(Monte Carlo tree search,MCTS)收敛速度过慢,且在博弈过程中关键节点会出现信息丢失等问题,以中国象棋为载体,构建适用于中国象棋博弈系统的策略价值网络,提出了一种基于统计数据的并行蒙特卡洛树搜索算法(parallel Monte Carlo tree search based on statistics,SPMCTS)。将并行化的重点设置在MCTS四个步骤中最耗时的扩展和模拟步骤,有效避免了算法执行过程中的等待时差。并且引入一组新统计数据,这些数据用于在MCTS的选择步骤中修改节点的选择策略,保证在进行节点选择时获取和利用更多的可用信息,缓解信息丢失对精度造成的影响。实验结果表明,与现有并行蒙特卡洛树算法相比,SPMCTS在搜索速度上加快了约34%,且在对弈实验中,博弈胜率也能保持在80%左右。验证了SPMCTS的有效性。
