Real-World Reinforcement Learning: Observations from Two Successful Cases

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

38 Lataukset (Pure)

Abstrakti

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.
AlkuperäiskieliEnglanti
OtsikkoProceedings of the 34th Bled eConference: Digital Support from Crisis to Progressive Change
KustantajaUniversity of Maribor Press
Sivut273
Sivumäärä285
ISBN (elektroninen)978-961-286-485-9
DOI - pysyväislinkit
TilaJulkaistu - 23 kesäk. 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaBled eConference: Digital Support from Crisis to Progressive Change - Virtual, Online
Kesto: 27 kesäk. 202130 kesäk. 2021

Conference

ConferenceBled eConference
KaupunkiVirtual, Online
Ajanjakso27/06/202130/06/2021

Sormenjälki

Sukella tutkimusaiheisiin 'Real-World Reinforcement Learning: Observations from Two Successful Cases'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä