Temperature parameter control of Q value-based Dynamic Programming with Boltzmann distribution
Temperature parameter control of Q value-based Dynamic Programming with Boltzmann distribution
复制标题
基于Q值的玻尔兹曼分布动态规划温度参数控制
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
K. Hirasawa
中科院分区：
文献类型：
--
作者：
Shanqing Yu;S. Mabu;M. K. Mainali;S. Eto;K. Shimada;K. Hirasawa
为了从全局角度提高交通系统的效率，提出了一种动态路径选择策略，该策略利用扩展的Q值动态规划算法计算每个OD对的最优行程时间，并通过调整玻尔兹曼分布中的温度参数来产生全局最优路径.本文详细讨论了如何根据动态交通条件来控制温度参数。此外，还对基于Q值的博茨曼分布动态规划的各种温度参数控制策略进行了仿真测试。结果表明，采用合适的温度参数控制策略可以有效提高交通系统的效率。Q值动态规划
In order to improve the efficiency of traffic systems in the global perspective, we proposed a dynamic routing strategy, where the optimal traveling time for each Origin-Destination (OD) pair is calculated by extended Q value-based Dynamic Programming and the global optimum routes are produced by adjusting the temperature parameter in Boltzmann distribution. In this paper, how to control the temperature parameter is discussed in detail depending on the dynamic traffic conditions. What's more, various temperature parameter control strategies of the Q value-based Dynamic Programming with Botzmann distribution are tested in the simulations. The results show that adopting suitable temperature parameter control strategy could improve the efficiency of the traffic systems effectively. Q value-based Dynamic Programming