Linear Fitted-Q Iteration with Multiple Reward Functions

机译：具有多个奖励函数的线性Fitd-Q迭代

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

We present a general and detailed development of an algorithm for finite-horizon fitted-Q iteration with an arbitrary number of reward signals and linear value function approximation using an arbitrary number of state features (Lizotte, Murphy, and Bowling 2012). This includes a detailed treatment of the 3-reward function case using triangulation primitives from computational geometry and a method for identifying globally dominated actions. We also present an example of how our methods can be used to construct a real-world decision aid by considering symptom reduction, weight gain, and quality of life in sequential treatments for schizophrenia. Finally, we discuss future directions in which to take this work that will further enable our methods to make a positive impact on the field of evidence-based clinical decision support.

机译：我们介绍了一种有限水平拟合Q迭代算法的一般和详细开发，该算法具有任意数量的奖励信号和使用任意数量的状态特征的线性值函数逼近（Lizotte，Murphy和Bowling 2012）。这包括使用来自计算几何的三角剖分图元对3奖赏函数情况的详细处理，以及用于识别全局支配动作的方法。我们还提供了一个示例，说明如何在精神分裂症的序贯治疗中考虑症状减轻，体重增加和生活质量，从而将我们的方法用于构建现实世界的决策辅助工具。最后，我们讨论了开展这项工作的未来方向，这些方向将进一步使我们的方法对基于证据的临床决策支持领域产生积极影响。

著录项

来源
《Proceedings of the Twenty-Third International conference on Automated planning and Scheduling》|2013年|474-475|共2页
会议地点 Rome(IT)
作者
Daniel J. Lizotte; Michael Bowling; Susan A. Murphy;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Linear Fitted-Q Iteration with Multiple Reward Functions [J] . Lizotte Daniel J., Bowling Michael, Murphy Susan A. Journal of machine learning research . 2012,第Nov期

机译：具有多个奖励函数的线性Fitd-Q迭代
2. Preferable Pareto optimal solutions for specified key objective functions to multiple objective linear programming problems using trade-off ratios under fuzzy environment: an iterative process [J] . Arindam Garai, Palash Mandal, Tapan Kumar Roy International Journal of Operational Research . 2019,第2期

机译：优选的Pareto用于指定关键目标功能的最佳解决方案，在模糊环境下使用权衡差值进行多个客观线性规划问题：一个迭代过程
3. Optimal iterative methods for finding multiple roots of nonlinear equations using weight functions and dynamics [J] . Zafar Fiza, Cordero Alicia, Sultana Sana, Journal of Computational and Applied Mathematics . 2018,第期

机译：使用权重函数和动态找到非线性方程多根根的最佳迭代方法
4. Linear Fitted-Q Iteration with Multiple Reward Functions [C] . Daniel J. Lizotte, Michael Bowling, Susan A. Murphy International Conference on Automated Planning and Scheduling . 2013

机译：具有多个奖励功能的线性拟合Q迭代
5. Optimal solution to patient-specific coefficients for electrocardiogram to vectorcardiogram conversion using iterative multiple linear regression. [D] . Morales, Eduardo. 2005

机译：使用迭代多元线性回归将心电图转换为矢量心电图的患者特定系数的最佳解决方案。
6. Linear Fitted-Q Iteration with Multiple Reward Functions [O] . Daniel J. Lizotte, Michael Bowling, Susan A. Murphy -1

机译：具有多个奖励功能的线性拟合Q迭代
7. Erratum to “Projection-proximal methods for general variational inequalities” J. Math. Anal. Appl. 318 (2006) 53–62. Erratum to “The improved LaSalle-type theorems for stochastic functional differential equations” J. Math. Anal. Appl. 318 (2006) 134–154. Erratum to “Iterative approximation of fixed points of nonexpansive mappings” J. Math. Anal. Appl. 318 (2006) 288–295. Erratum to “On the stability of the orthogonal Pexiderized Cauchy equation” J. Math. Anal. Appl. 318 (2006) 211–223. Erratum to “On semilinear elliptic equations involving concave–convex nonlinearities and sign-changing weight function” J. Math. Anal. Appl. 318 (2006) 253–270 [O] . The Publisher 2006

机译：勘误表“一般变分不等式的投影近邻方法” J．数学。肛门应用318（2006）53-62。勘误“对随机泛函微分方程的改进的LaSalle型定理” J.数学。肛门应用318（2006）134–154。勘误表为“非膨胀映射的不动点的迭代逼近” J.数学。肛门应用318（2006）288–295。勘误表“关于正交Pexiderized Cauchy方程的稳定性” J.数学。肛门应用318（2006）211–223。参见“关于涉及凹凸非线性和符号变权函数的半线性椭圆方程”的勘误。数学。肛门应用318（2006）253–270

Linear Fitted-Q Iteration with Multiple Reward Functions

摘要

著录项

相似文献

相关主题

期刊订阅