搜索资源列表
muti-agents-toolbox
- 多智能体工具包，可直接用来进行多智能体强化学习算法设计与仿真
AI_Life
- The project aims at developing a program which could demonstrate and simulate Artificial Life. The project implements three main technologies which are used in the Gaming industry and Robotics for coding intelligent agents. These are: Neural Net
bucuo
- 针对现有入侵 检测系统的不足,对数据挖掘技术和智能检测代理应用于入侵检测系统进行了研究,提出一个基于数据挖掘技 术的智能入侵检测系统模型-Intrusion detection system for the existing shortage of data mining and intelligent detection agents used in intrusion detection systems have been studied, proposed a data min
Agents_in_Computer_Games
- Introcude Agents in Computer Games.
vwumpus
- 智能体Wumpus，可实现智能体找金子游戏，这样，主要应用于Agent技术，人工智能方面的研究-Agent Wumpus, enables agents to find gold game, so that is mainly used in Agent technologies, artificial intelligence research
Multi-Agent-Particle-Swarm-Algorithm
- 结合多智能体的学习、协调策略及粒子群算法，提出了一种基于多智能体粒子群优化的配电网络重构方法。该方法采用粒子群算法的拓扑结构来构建多智能体的体系结构，在多智能体系统中，每一个粒子作为一个智能体，通过与邻域的智能体竞争、合作。能够更快、更精确地收敛到全局最优解。粒子的更新规则减少了算法不可行解的产生，提高了算法效率。实验结果表明，该方法具有很高的搜索效率和寻优性能。-Combining the study of multi-agent technology，coordinating strateg
1
- Current debates regarding the possible cognitive implications of ideas from adaptive behavior research and dynamical systems theory would benefit greatly from a careful study of simple model agents that exhibit minimally cognitive behavior. T
code
- This course describes the AI techniques necessary for an agent to act intelligently in the ``real world. Techniques include natural language processing, uncertainty reasoning, learning, vision and speech processing. Basic AI techniques (such as searc
napping
- 非参数政策梯度的napping机制的java代码参考文献：Qing Da, Yang Yu, and Zhi-Hua Zhou. Napping for Functional Representation of Policy. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 14), Paris, France, 2014.-This
game-theory
- We consider the scheduling of simple linear deteriorating jobs on parallel machines a new perspective based on game theory. In scheduling, jobs are often controlled by independent and selfish agents, in which each agent tries to a machine for process
1709.04326
- 多智能体设置在机器学习中的重要性日益突出。超过了最近的大量关于深度的工作多agent强化学习，层次强化学习，生成对抗网络和分散优化都可以看作是这种设置的实例。然而，多学习代理人的存在这些设置使得培训问题的非平稳常常导致不稳定的训练或不想要的最终结果。我们提出学习与对手的学习意识（萝拉），一种方法，原因的预期。其他代理的学习。罗拉学习规则包括一个额外的术语，解释了在预期的参数更新的代理政策其他药物。我们发现，利用似然比策略梯度更新的方法，可以有效地计算萝拉更新规则，使该方法适合于无模型强化学习。这