q learning

This sample graph is from a simple reinforcement learning application that uses Q learning.

这个示例图是从使用Q学习的一个简单增强式学习应用程序中得到的。

Discretization of the state and decision spaces is required when Q Learning is used to solve stochastic optimal control problems with continuous state and decision spaces.

要用Q学习算法来求解有连续状态和决策空间的随机最优控制问题，则需要先离散化问题的状态和决策空间。

A New Q Learning Algorithm for Multi-agent Systems

一种新的多智能体Q学习算法

The priority of handoff call is improved by giving it a greater reward, and we use event-driven Q learning algorithm to solve the problem.

通过赋予切换呼叫更大的报酬提高切换呼叫的优先级，并采用事件驱动Q学习算法求解该问题。

Q learning is of great importance in reinforcement learning.

Q学习是一种重要的强化学习算法。

Car used to enhance learning ( Q learning), using neural network Q function approximation.

小车采用加强学习（Q learning），采用神经网络对Q函数逼近。

In this paper, a mechanism of behavior learning for soccer robot action selection based on Q learning and case based learning is proposed.

提出了一种足球机器人基于Q学习与案例学习（CBL）相结合的自主学习机制。

An Autonomous Agent Model Based on Q Learning

基于Q学习的自主Agent模型

Convergence of Discretization Procedure in Q Learning Improved fuzzy arithmetic operator with discretization procedure for fuzzy fault tree new analysis

Q学习算法中网格离散化方法的收敛性分析基于离散化修正模糊算子的模糊故障树新析

The paper had the main achievements as follows: ( 1) Based on Q learning algorithm storing information by table, the paper proposes the improved Q learning based on neural networks.

论文取得以下主要成果：（1）在表格型Q学习算法的基础上，提出了一种基于神经网络的改进的Q学习方法。

To the research of non-cooperative multi-agent system, it has obvious advantages to game equilibrium strategy, so this paper researches cooperation climate strategy which used Q learning algorithm based Nash and Meta equilibrium.

而研究非合作多Agent系统，博弈均衡策略有着其明显优势，所以本文利用基于Nash平衡和Meta平衡的Q学习算法分别对气候合作策略进行了研究。

The pre-posture adjusts the robot pose with the method of FSM. The climbing adopts the fuzzy Q learning to maintain the stability of the process.

姿态预调整利用有限状态机来实现：推进过程通过模糊Q学习保持推进过程的平稳性。

Finally, simulation examples illustrate that, compared to always accept policy, the event-driven Q Learning can heighten profit and lower handoff call dropping probability.

最后通过仿真实例说明，与总是接受策略相比，事件驱动Q学习能够提高网络收益，降低切换呼叫掉线率。

Finally, the learning speed of Q learning algorithm is very slow.

最后，Q学习算法的学习速度较慢。

To solve the problem of slow update speed in Q learning, a multi-step Q learning scheduling algorithm is proposed, in which the value function is updated based on the information in multiple steps.

针对任务调度的Q学习算法更新速度慢的问题，提出一种基于多步信息更新值函数的多步Q学习调度算法。

Multi-Step Q Learning Algorithm for Task Scheduling in Collaborative Design

协同设计任务调度的多步Q学习算法

The paper first presents an objective model of task scheduling, and then based on the analysis of Q learning algorithm, the Markov decision process description of the scheduling problem is given.

首先建立任务调度问题的目标模型，在分析Q学习算法的基础上，给出调度问题的马尔可夫决策过程描述；

Stochastic Scheduling Algorithm for Multiple Mould and Die Manufacturing Projects Based on Multi-step Q Learning

基于多步Q学习的模具制造项目群随机调度算法

The Q Learning System Based on The Priori Knowledge And The Application to The Robot Soccer

基于模糊先验知识的Q学习及在足球机器人系统中的应用

The higher layer is a Q Learning unit defined on the space of combined action, its responsibility is the selection of a proper combined actions.

高层是建立在组合单元动作空间上的Q学习单元，实现组合动作的选择。

Q learning algorithm is the most popular reinforcement learning algorithm, but the algorithm exist some problems.

目前主流的强化学习算法是Q学习算法，但Q学习本身存在一些问题。

Metropolis Policy-based Multi-step Q Learning Algorithm and Performance Simulation

基于Metropolis准则的多步Q学习算法与性能仿真

The Research and Implementation of Agent Intelligent Decision Based on Q Learning

基于Q学习的Agent智能决策的研究与实现

In order to serve users with more accurate information, the Agent collaborative filtering model& ACFM based on users 'feedback and the dynamic Q learning algorithm are put forward, and users' interesting model is built.

为了提供给用户更准确的信息，提出基于用户反馈的智能合作过滤模型和一种基于用户兴趣的动态Q学习算法，并建立用户兴趣模型。

A multi step Q learning algorithm was employed to overcome the slow convergence rate of standard Q learning, and CMAC neural network was used to generalize the continuous state space.

为解决连续过程的学习问题，采用CMAC神经网络对连续状态空间进行泛化。

For the learning problem of agent team cooperation, the basic Q learning algorithm is extended by introducing the concept of leading agent and setting the reward assignment policy among several learning agents.

最后，针对Agent团队协作的学习问题，对单Agent的Q学习算法进行了扩展。主要思想是引入主导Agent的概念，并考虑将环境奖赏按照一定策略分配给多个Agent，实现同时学习。

States are clustered in order to reduce the state space, Q learning algorithm is used to get the table of Q values, then the available action is selected according to the Q value table.

用状态聚类减小状态空间，利用Q学习算法获得Q值表，根据学习后的Q值表选择动作。

The agent has a high intelligence and can improve the learning ability according to the dynamic environment with the ability of Q learning.

学习使智能体具有较高的智能性，可以通过提高自己的学习能力适应不断变化的动态环境。

Through studying Markov decision-making process and reinforcement learning algorithm, have designed the shoot module based on Q learning method.

通过研究Markov决策过程与再励学习算法，设计了基于Q学习方法的射门模块。

Study of Behavior Learning for Soccer Robot Based on Q Learning and CBL

基于Q学习与CBL结合的机器人足球行为学习研究