助手标题  
全文文献 工具书 数字 学术定义 翻译助手 学术趋势 更多
查询帮助
意见反馈
   markov games 的翻译结果: 查询用时:0.203秒
图标索引 在分类学科中查询
所有学科
自动化技术
更多类别查询

图标索引 历史查询
 

markov games
相关语句
  markov对策
     Markov Games Based Reinforcement Learning and its Application in RoboCup
     基于Markov对策的强化学习及其在RoboCup中的应用
短句来源
     In multi-agent coordination methods, the multi-agent learning and Markov games are researched and analyzed.
     在多Agent协调的学习与对策中,重点研究与分析了多Agent强化学习算法和Markov对策
短句来源
     Each AGV is treated as a rational agent in the system, which has two level decisions: on the option level, an agent adopts a reinforcement learning method under the Markov games architecture and makes decision to execute a subtask with the best response to the other AGV's current option;
     系统中的每一个 AGV都由一个具有两级决策能力的智能体控制 :在选择级 ,智能体采用 Markov对策框架下的强化学习方法 ,以根据其他 AGV当前的子任务建立自己的最有反应子任务 ;
短句来源
     And the minmax-Q learning algorithm could only solve the problem of zero-sum Markov games. In this paper, the non-zero-sum Markov games are adopted as a framework for multi-agent reinforcement learning, and the learning model and learning algorithms of the metagame reinforcement learning are brought forward. It is proved that this metagame-Q algorithms must converge at the most optimal value of the non-zero-game Markov games.
     在MDP中,单Agent可以通过强化学习来寻找问题的最优解.但在多Agent系统中,MDP模型不再适用.同样极小极大Q算法只能解决采用零和对策模型的MAS学习问题.文中采用非零和Markov对策作为多Agent系统学习框架,并提出元对策强化学习的学习模型和元对策Q算法.理论证明元对策Q算法收敛在非零和Markov对策的元对策最优解.
短句来源
     In this paper,Markov games as a framework for reinforcement learning are studied. The learning model and algorithm for complex problems such as Decision-Making in RoboCup Simulation are brought forward.
     论文研究了Markov对策模型作为学习框架的强化学习,提出了针对RoboCup仿真球队决策问题这一类复杂问题的学习模型和具体算法。
短句来源
更多       
  “markov games”译为未确定词的双语例句
     Survey of Multi-agent Reinforcement Learning in Markov Games
     随机博弈框架下的多agent强化学习方法综述
短句来源
     Based on this point, the thesis integrates Markov Games with reinforcement learning and makes preliminary explorations into the cooperative game reinforcement learning methods for multi-agents.
     本文正是基于这一点,将马尔可夫博弈与强化学习结合起来,对多Agent的协同博弈强化学习方法进行了初探。
短句来源
     Furthermore, Markov Games and reinforcement learning are merged into MAS with certain constraints so that preliminary explorations have been made to study the cooperative game reinforcement learning.
     此外,通过施加一定的约束,将马尔可夫博弈与强化学习相结合并应用到多Agent系统中,对协同博弈强化学习进行了初探。
短句来源
  相似匹配句对
     Analysis of the Medals Distribution of Olympic Games with Markov Method
     奥运会奖牌分布的Markov分析
短句来源
     Survey of Multi-agent Reinforcement Learning in Markov Games
     随机博弈框架下的多agent强化学习方法综述
短句来源
     NEW GAMES
     新游戏
短句来源
     Games in P E Teaching
     体育游戏在体育教学实践中的应用和作用
短句来源
     The application of Markov chain
     Markov链的一种应用
短句来源
查询“markov games”译词为用户自定义的双语例句

    我想查看译文中含有:的双语例句
例句
为了更好的帮助您理解掌握查询词或其译词在地道英语中的实际用法,我们为您准备了出自英文原文的大量英语例句,供您参考。
  markov games
We present some existing tools for solving finite horizon and infinite horizon discounted Markov games with unbounded cost, and develop new ones that are typically applicable in queueing problems.
      
Zero-sum Markov games and worst-case optimal control of queueing systems
      
In this paper, we consider two-person zero-sum discounted Markov games with finite state and action spaces.
      
Discounted Markov games: Generalized policy iteration method
      
Three kinds of zero-sum Markov games with stopping and impulsive strategies are considered.
      
更多          


In Markov decision process, a single agent could find the optimal policy of the problem by reinforcement learning. But the model of the MDP doesn't adapt to the multi-agent system. And the minmax-Q learning algorithm could only solve the problem of zero-sum Markov games. In this paper, the non-zero-sum Markov games are adopted as a framework for multi-agent reinforcement learning, and the learning model and learning algorithms of the metagame reinforcement learning are brought forward. It is...

In Markov decision process, a single agent could find the optimal policy of the problem by reinforcement learning. But the model of the MDP doesn't adapt to the multi-agent system. And the minmax-Q learning algorithm could only solve the problem of zero-sum Markov games. In this paper, the non-zero-sum Markov games are adopted as a framework for multi-agent reinforcement learning, and the learning model and learning algorithms of the metagame reinforcement learning are brought forward. It is proved that this metagame-Q algorithms must converge at the most optimal value of the non-zero-game Markov games.

在MDP中,单Agent可以通过强化学习来寻找问题的最优解.但在多Agent系统中,MDP模型不再适用.同样极小极大Q算法只能解决采用零和对策模型的MAS学习问题.文中采用非零和Markov对策作为多Agent系统学习框架,并提出元对策强化学习的学习模型和元对策Q算法.理论证明元对策Q算法收敛在非零和Markov对策的元对策最优解.

Non zero sum Markov game and reinforcement learning based on Q algorithm is a feasible frame for the research on the mechanism of multiagent system's cooperation. In fact, the independent learning is accentuated for agent regardless of other agents' actions under this frame. So, the mechanism of cooperation is deficient. And, it is over idealized that the perfect observed information is required when agents are interacting with environment. In the paper, cooperated learning under joined action and...

Non zero sum Markov game and reinforcement learning based on Q algorithm is a feasible frame for the research on the mechanism of multiagent system's cooperation. In fact, the independent learning is accentuated for agent regardless of other agents' actions under this frame. So, the mechanism of cooperation is deficient. And, it is over idealized that the perfect observed information is required when agents are interacting with environment. In the paper, cooperated learning under joined action and imperfect information was proposed for solving these two problems. Convergence of the improving algorithm was proved.

MAS的协作机制研究 ,当前比较适用的研究框架是非零和 Markov对策及基于 Q-算法的强化学习 .但实际上在这种框架下的 Agent强调独立学习而不考虑其他 Agent的行为 ,故 MAS缺乏协作机制 .并且 ,Q-算法要求 Agent与环境的交互时具有完备的观察信息 ,这种情况过于理想化 .文中针对以上两个不足 ,提出了在联合行动和不完备信息下的协调学习 .理论分析和仿真实验表明 ,协调学习算法具有收敛性 .

This research presented a multilevel decision and cooperative learning method to build dynamic and distributed dispatching policies that an AGV needs in an AGV dispatching system. Each AGV is treated as a rational agent in the system, which has two level decisions: on the option level, an agent adopts a reinforcement learning method under the Markov games architecture and makes decision to execute a subtask with the best response to the other AGV's current option; on the action level, an agent learns an...

This research presented a multilevel decision and cooperative learning method to build dynamic and distributed dispatching policies that an AGV needs in an AGV dispatching system. Each AGV is treated as a rational agent in the system, which has two level decisions: on the option level, an agent adopts a reinforcement learning method under the Markov games architecture and makes decision to execute a subtask with the best response to the other AGV's current option; on the action level, an agent learns an optimal policy of actions for achieving its planned option. Finally, an AGV's dispatching simulation testifies that the method will bring more throughput for the system and keep the throughput stable when the ratio of parts arrival changes.

提出基于多级决策和协作学习的方法来建立自动导航车 ( AGV)调度系统中每个 AGV所需要的动态分布式调度策略 .系统中的每一个 AGV都由一个具有两级决策能力的智能体控制 :在选择级 ,智能体采用 Markov对策框架下的强化学习方法 ,以根据其他 AGV当前的子任务建立自己的最有反应子任务 ;在行动级 ,智能体通过强化学习建立优化的动作策略来完成由选择级确定的子任务 .AGV调度仿真结果证明 ,该方法能提高系统的产量 ,并在零件到达比变化时保持输出产量的稳定

 
<< 更多相关文摘    
图标索引 相关查询

 


 
CNKI小工具
在英文学术搜索中查有关markov games的内容
在知识搜索中查有关markov games的内容
在数字搜索中查有关markov games的内容
在概念知识元中查有关markov games的内容
在学术趋势中查有关markov games的内容
 
 

CNKI主页设CNKI翻译助手为主页 | 收藏CNKI翻译助手 | 广告服务 | 英文学术搜索
版权图标  2008 CNKI-中国知网
京ICP证040431号 互联网出版许可证 新出网证(京)字008号
北京市公安局海淀分局 备案号:110 1081725
版权图标 2008中国知网(cnki) 中国学术期刊(光盘版)电子杂志社