Reinforcement Learning and Stochastic Optimization: A universal framework for sequential decisions
Reinforcement Learning and Stochastic Optimization: A unified framework for sequential decisions
This textbook is the first to offer a comprehensive, unified framework of the rich field of sequential decisions under uncertainty. Up to now, this rich problem class has been fragmented into at least 15 distinct fields that have been studied under names such as dynamic programming, stochastic programming, optimal control, simulation optimization, optimal learning, and multi-armed bandit problems. Recently these have been primarily associated with “reinforcement learning” and “stochastic optimization.”
Use the form below to get a copy of the white paper.
"Carriers have long been seeking network optimization that is both dynamic and holistic, covering all loads, trucks, and drivers simultaneously.”
Zach Schuchart - Head of Sales, Optimal Dynamics