1) Roth-Erev reinforcement learning method
Roth-Erev加强学习法
2) Roth-Erev learning model
Roth-Erev学习模型
3) reinforcement learning
加强学习
1.
It is hard to apply reinforcement learning algorithms to solve elevator group control problem in a building with more floors and elevators.
运用加强学习算法解决电梯群控问题往往受限于算法收敛速度慢,很难扩展至具有更高楼层、更多电梯的群控系统。
2.
he problem of real time modeling of the time series single-step forecasting model based-on neural networks can be viewed as a reinforcement learning problem.
提出了将基于神经网络的时序一步预测模型的实时建模预测问题归结为加强学习问题，从而提出用时差法和误差反向传播法分别解决时间信用赋值问题和结构信用赋值问题。
4) watkins's Q(λ)reinforcement learning
自加强Watkins'sq(λ)学习算法
6) enhanced learning path
学习加强路径
1.
An effective algorithm to find the enhanced learning path is proposed which can establish enhanced learning path for each learner and give individual guidance.
并通过学习加强路径算法为每个学生建立学习加强路径,对学生进行个别化指导。
补充资料：[3-(aminosulfonyl)-4-chloro-N-(2.3-dihydro-2-methyl-1H-indol-1-yl)benzamide]
分子式：C16H16ClN3O3S
分子量：365.5
CAS号：26807-65-8
性质：暂无
制备方法：暂无
用途：用于轻、中度原发性高血压。
分子量：365.5
CAS号：26807-65-8
性质：暂无
制备方法：暂无
用途：用于轻、中度原发性高血压。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条