Real-World Reinforcement Learning: Observations from Two Successful Cases

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

83 Downloads (Pure)

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.
Original languageEnglish
Title of host publicationProceedings of the 34th Bled eConference: Digital Support from Crisis to Progressive Change
PublisherUniverza v Mariboru
Pages273
Number of pages285
ISBN (Electronic)978-961-286-485-9
DOIs
Publication statusPublished - 23 Jun 2021
MoE publication typeA4 Conference publication
EventBled eConference: Digital Support from Crisis to Progressive Change - Virtual, Online
Duration: 27 Jun 202130 Jun 2021

Conference

ConferenceBled eConference
CityVirtual, Online
Period27/06/202130/06/2021

Keywords

  • reinforcement learning
  • AI adoption
  • thematic analysis
  • machine learning
  • self-learning agents

Fingerprint

Dive into the research topics of 'Real-World Reinforcement Learning: Observations from Two Successful Cases'. Together they form a unique fingerprint.

Cite this