发表机构
Independent Consultant(独立顾问)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文提出结合深度神经网络与线性规划归一化的函数逼近方法,以减少高维动态规划中的贝尔曼误差,并在收益管理网络容量控制问题上验证了其竞争力。
AI 中文摘要
本文提出了一种新的函数逼近方法,用于减少高维动态规划和强化学习问题中的贝尔曼误差。以经典的动态规划问题(收益管理中的网络容量控制)作为激励示例,本文阐述了深度神经网络与线性规划逼近算法可以相结合,以推导动态规划问题的近似解。仿真结果表明,所提出的逼近算法在与基准比较时达到了具有竞争力的性能。
英文摘要
This paper proposes a new functional approximation approach to reduce Bellman error in high-dimensional dynamic programming and Reinforcement Learning problems. Using a classic dynamic programming problem (network capacity control in revenue management) as the motivational example, the paper illustrates that deep neural networks and linear programming approximation algorithms can be combined to derive approximate solutions to dynamic programming problems. Simulation results show the proposed approximation algorithms achieves competitive performance when compared with benchmark.