搜索资源列表
deboor-cox.rar
- 目的:运用强化学习!多分类器集成!降维方法等最新计算机技术,结合细胞病理知识,设计制作/智能化肺癌细胞病理图像诊断系统0"方法:采集细胞图像,运用基于强化学习的图像分割法将细胞区域从背景中分离出来 运用基于样条和改进2方法对重叠细胞进行分离和重构 提取40个细胞特征用于贝叶斯!支持向量机!紧邻和决策树4种分类器,集成产生肺癌细胞分类结果 建立肺癌细胞病理图库,运用基于等降维方法对细胞进行比对,给予未定型癌细胞分类"结果:/智能化肺癌细胞病理诊断系统0应用于临床随机1200例肺
ReinforcementLearning
- 强化学习的原代码还可以的 -The original source of reinforcement learning reinforcement learning can also be in the original code
Q-learning-Reinforcement-learning
- 强化学习matlab源代码很少见的源代码，详细介绍Q学习的编程过程。-Reinforcement learning matlab source code，rare source code, detailed Q learning programming.
Q-learning
- 关于增强学习的一个例子，Q-learning算法，和大家分享。-An example of reinforcement learning, and to share.
TicTacToe
- 将强化学习算法应用于Tic-tac-toe游戏-The reinforcement learning algorithm is applied to Tic-tac-toe game
reinforcement
- 贝叶斯学习与强化学习结合技术的研 详细介绍了强化学习的算法和理论-Bayesian learning and reinforcement learning combined with the technical details of the study of reinforcement learning algorithms and theory
RL2
- reinforcement learning
2007-03-23_approxrl
- approximate reinforcement learning
Torch3win
- the example and toolbox for machine learning（under windows platform）including all the widely used method such as monte carlo method,reinforcement learning method and so on
ReinforcementLearning
- 这是机器学习里面的强化学习的重要资料，主要介绍了强化学习的基本理论及实验和分析-This is inside the machine learning reinforcement learning important information, which mainly describes the basic theory of reinforcement learning and experimental and analytical
main
- 在各种非线性系统中，倒立摆是一典型例子，用强化学习实现控制倒立摆-on-line learning control by association and reinforcement
Buterfly
- Artificial intelligence with Reinforcement learning.
SuttonBArtoReinforcementlearning
- sutton and barto books on reinforcement learning
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
RL
- 采用vs2008 c#编写 Q-Learning强化学习的代码实现 状态空间5维，动作空间5维-Using vs2008 c# Q-Learning reinforcement learning the code to achieve the state-space five-dimensional, five-dimensional action space
nc_tanker
- Neural control (reinforcement learning) for tanker heading
whjt05_iros
- Multi-Agent Quadrotor Testbed Control Design: Integral Sliding Mode vs. Reinforcement Learning
Main
- AI Reinforcement Learning 走格子， 输出每1000步达到目标格子次数。reward: goal-> +1 rest -> 0.-Java implementation for an Reinforcement Learning agent to search through a Grid World from start point to goal state. reward: goal->+1 rest-> 0.
Reinforcement-Learning
- Reinforcement Learning
Reinforcement Learning：An Introduction
- 在这本书中，我们探索了一种从交互中学习的计算方法。我们不直接对人或动物如何学习进行理论分析，而是探索理想化的学习情境，评估各种学习方法的效率。也就是说，我们采用人工智能研究人员或工程师的角度。我们探索去设计在这些方面上格外有效率的机器，他能够解决科学或经济学领域的问题。通过数据分析和计算实验来评估这些设计。我们将这种方法称为强化学习，更侧重于目标导向的交互学习，而不是其他方法。(In this book, we explored a computational method of learnin