A NewMulti-agent Reinforcement Learning Approach

机译：一种新的多功能加强学习方法

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

A new multi-agent reinforcement learning approach is proposed to learn the optimal behaviors among cooperative agent teams. The approach combines advantages of the integer programming, single agent learning and repeated game in a multi-agent framework. The integer programming is used to build cooperative teams in order to prevent the curse of dimensionality. Every cooperative team learns independently, whose members take the best response actions in the light of other agents actions in the same condition, after many repeated games, the aim root could be found. Because of other agents influence, the process of learning is supervised periodically, then through changing the learning rate to gain the right learning results. Simulation results on pursuit problem show that the proposed learning approach overcomes the divergence and improves learning speed obviously.

机译：提出了一种新的多档强化学习方法，以学习合作社团队中的最佳行为。该方法将整数编程，单代理学习和重复游戏中的整数编程，重复游戏的优势结合在一起。整数编程用于构建合作团队，以防止维度的诅咒。每个合作团队都独立学习，其成员在同一条件下的其他代理行动中采取最佳反应行动，在许多重复的游戏之后，可以找到目标根。由于其他代理的影响，学习过程是定期监督的，然后通过改变学习率来获得正确的学习结果。追求问题的仿真结果表明，建议的学习方法克服了发散，显然提高了学习速度。

著录项

来源
《IEEE International Conference on Information and Automation》|2010年||共5页
会议地点
作者
Jun Li; Qishu Pan; Bingrong Hong;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类 TP2-53;
关键词
Multi-agent; System(MAS); Reinforcement learning; Q-learning; Pursuit problem;

机译：多助剂;系统（MAS）;加固学习;Q-Learning;追求问题;

相似文献

外文文献
中文文献
专利

1. Accuracy-Based Learning Classifier Systems for Multistep Reinforcement Learning: A Fuzzy Logic Approach to Handling Continuous Inputs and Learning Continuous Actions [J] . Gang Chen, Colin I. J. Douch, Mengjie Zhang IEEE transactions on evolutionary computation . 2016,第6期

机译：基于精度的多步强化学习分类器系统：处理连续输入和学习连续动作的模糊逻辑方法
2. Reinforcement Learning Approach for Adaptive E-learning Systems using Learning Styles [J] . Balasubramanian Velusamy, S. Margret Anouneia, George Abraham Information Technology Journal . 2013,第12期

机译：使用学习方式的自适应电子学习系统的强化学习方法
3. Reinforcement Learning Approach for Adaptive E-learning Systems using Learning Styles [J] . Balasubramanian Velusamy, S. Margret Anouneia, George Abraham Information Technology Journal . 2013,第12期

机译：使用学习方式的自适应电子学习系统的强化学习方法
4. A NewMulti-agent Reinforcement Learning Approach [C] . Jun Li, Qishu Pan, Bingrong Hong Proceedings of the 2010 IEEE International Conference on Information and Automation . 2010

机译：一种新的多主体强化学习方法
5. Improving Learning and Reducing Time: A Constrained Action Based Reinforcement Learning Approach [D] . Shen, Shitian. 2019

机译：改善学习和减少时间：基于约束的加强学习方法
6. Correction: Linking Individual Learning Styles to Approach-Avoidance Motivational Traits and Computational Aspects of Reinforcement Learning [O] . Kristoffer Carl Aberg, Kimberly C. Doell, Sophie Schwartz -1

机译：纠正：将个人学习风格与避免方法的动机特征和强化学习的计算方面联系起来
7. A fast learning approach for autonomous navigation using a deep reinforcement learning method [O] . Muhammad Mudassir Ejaz, Tong Boon Tang, Cheng‐Kai Lu 2021

机译：利用深增强学习方法的自主导航快速学习方法

A NewMulti-agent Reinforcement Learning Approach

摘要

著录项

相似文献

相关主题

期刊订阅