Real-World Reinforcement Learning: Observations from Two Successful Cases

Abstract

Reinforcement Learning (RL) is a machine learning technique that enables artificial agents to learn optimal strategies for sequential decision-making problems. RL has achieved superhuman performance in artificial domains, yet real-world applications remain rare. We explore the drivers of successful RL adoption for solving practical business problems. We rely on publicly available secondary data on two cases: data center cooling at Google and trade order execution at JPMorgan. We perform thematic analysis using a pre-defined coding framework based on the known challenges to real-world RL by DulacArnold, Mankowitz, & Hester (2019). First, we find that RL works best when the problem dynamics can be simulated. Second, the ability to encode the desired agent behavior as a reward function is critical. Third, safety constraints are often necessary in the context of trial-and-error learning. Our work is amongst the first in Information Systems to discuss the practical business value of the emerging AI subfield of RL.