Reinforcement Learning Use Case

 

 

 

 

Speeding design and product development

Reinforcement learning can improve the development of products, engineering systems, manufacturing plants, oil refineries, telecommunications or utility networks, and other capital projects. Mining companies could, for example, explore a greater range of mine designs than possible with the other AI techniques used today to improve yield. One automotive manufacturer is already exploring how agents trained through reinforcement learning can enable it to test more ideas for regenerative braking in new electric vehicles, so it can optimize the design for noise, vibration, and heat.

Optimizing complex operations

Reinforcement learning’s ability to solve complex problems gives it high potential for optimizing complex operations. Initially, we see three primary applications of reinforcement learning in this area.

First, reinforcement learning can help organizations identify the right actions to take across a value chain as events unfold. A transportation company, for example, can optimize travel routes in real time based on changing traffic, weather, and safety conditions. A food producer can optimize product distribution worldwide amid daily, even hourly, fluctuating demand and exchange rates, varying shipping routes, and more.

It also can help teams manage complex manufacturing processes. For example, it can allow teams to monitor production in real time, simulating different scenarios and updating key parameters to increase production dynamically. Manufacturers that have already used machine learning to minimize product defects can now expand their insights with reinforcement learning to prevent the rare remaining defects that pop up intermittently with seemingly no common root cause.

Finally, reinforcement learning can power autonomous system controllers by, for instance, continuously monitoring and adjusting equipment operating temperatures to ensure optimal performance or running a robotic arm on the manufacturing floor.

Informing the next best action for each customer

When integrated within personalization and recommender systems, reinforcement learning can help organizations understand, identify, and respond to changes in taste in real time, personalizing messages and adapting promotions, offers, and recommendations daily.

 

www.mckinsey.com/business-functions/mckinsey-analytics/our-insights/its-time-for-businesses-to-chart-a-course-for-reinforcement-learning

It’s time for businesses to chart a course for reinforcement learning