#DeepReinforcementLearning #OperationsResearch #MaximizingProfits Dr. Barrett Thomas, an esteemed Research Professor in at the University of Iowa's College of Business, delves deep into Markov decision processes and how they relate to Deep Reinforcement Learning. Dr. Thomas explains how these advanced methodologies are revolutionizing operations research, leading to significant improvements in business strategies aimed at minimizing costs and maximizing profits. Moreover, the episode shines a light on the practical applications of these theories in real-world scenarios, such as enhancing the efficiency of same-day delivery services and paving the way for the future of supply chains with the advent of aerial drones and autonomous vehicles. This episode is brought to you by Ready Tensor, where innovation meets reproducibility (https://www.readytensor.ai/). Interested in sponsoring a SuperDataScience Podcast episode? Visit https://passionfroot.me/superdatascience for sponsorship information. In this episode you will learn: • [00:00:00] Introduction • [00:01:22] Barrett's start in operations logistics • [00:08:54] Concorde Solver and the traveling salesperson problem • [00:18:11] Cross-function approximation explained • [00:25:07] How Markov decision processes relate to deep reinforcement learning • [00:32:39] Understanding policy in decision-making contexts • [00:45:46] Revolutionizing supply chains and transportation with aerial drones • [00:51:18] Barrett’s career evolution: past changes and future prospects Additional materials: https://www.superdatascience.com/773