搜索资源列表
Q_learning
- 强化学习是人工智能中策略学习的一种，基于预期最大利益原则。和博弈论有密切的关系，也是多主体系统学习的常用方法。-Reinforcement learning is a kind of artificial intelligence in the strategic study, based on the principle of best interests is expected. And game theory are closely related, but also multi-agen
whjt05_iros
- Multi-Agent Quadrotor Testbed Control Design: Integral Sliding Mode vs. Reinforcement Learning
multiagentprogramming
- 一个多职能体的介绍资料,很好,值得学学,是英文资料,里面有例子-A Multi-agent Cooperative Reinforcement Learning
Usithod
- 利用聚类分析法改进的多Agent协作强化学习方法-Using cluster analysis to improve collaborative multi-Agent Reinforcement Learning Method
Adaptive-Fuzzy-Function-Approximation-for-Multi-A
- Adaptive Fuzzy Function Approximation for Multi-Agent Reinforcement Learning
Multi-Agent-Reinforcement-Learning
- 基于多Agent的学习博弈算法，可以实现多种算法，比如Minmax,FriendQ等，接口可扩展，实现较方便。-Multi-Agent-based learning game algorithm can achieve a variety of algorithms, such as Minmax, FriendQ and other interfaces can be extended to achieve more convenient.
Mmutti-agentsu
- 多智能体工具包，可直接用来进行行多智能体强化学习算法设计与仿真 -Multi-agent toolkit, can be directly used for design and simulation of the line multi-agent reinforcement learning algorithm
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
MAgent-master
- 多智能体的一段代码，有关强化学习，机器学习，很实用的一段代码！(A code of multi-agent, about reinforcement learning, machine learning, a very practical piece of code!)
Multi-Agent-Reinforcement-Learning-Environment
- 多智能体强化学习环境，用于开发强化学习算法(Multi agent reinforcement learning environment)
reinforcement-learning-master
- 在障碍物环境下的基于强化学习的单智能体与多智能体路径规划算法(Single agent and multi-agent path planning algorithm based on reinforcement learning in obstacle environment)
HDPONLINE
- 一段论文的代码实现 论文题目Multi-agent discrete-time graphical games and reinforcement learning solutions(Multi-agent discrete-time graphical games and reinforcement learning solutions)