Cracking open the black box: What observations can tell us about reinforcement learning agents

Arnaud Dethise; Marco Canini; Srikanth Kandula

doi:10.1145/3341216.3342210

Cracking open the black box: What observations can tell us about reinforcement learning agents

Arnaud Dethise, Marco Canini, Srikanth Kandula

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

30 Scopus citations

Abstract

Machine learning (ML) solutions to challenging networking problems, while promising, are hard to interpret; the uncertainty about how they would behave in untested scenarios has hindered adoption. Using a case study of an ML-based video rate adaptation model, we show that carefully applying interpretability tools and systematically exploring the model inputs can identify unwanted or anomalous behaviors of the model; hinting at a potential path towards increasing trust in ML-based solutions.

Original language	English (US)
Title of host publication	Proceedings of the 2019 Workshop on Network Meets AI & ML - NetAI'19
Publisher	ACM Press
Pages	29-36
Number of pages	8
ISBN (Print)	9781450368728
DOIs	https://doi.org/10.1145/3341216.3342210
State	Published - Aug 14 2019

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledgements: We thank the anonymous reviewers for their feedback. We are grateful to Nikolaj Bjørner, Bernard Ghanem, Hao Wang and Xiaojin Zhu for their valuable comments and suggestions. We also thank the Pensieve authors, in particular Mohammad Alizadeh and Hongzi
Mao, for their help and feedback.

Access to Document

10.1145/3341216.3342210

https://repository.kaust.edu.sa/bitstream/10754/658663/1/cotbb.netai19.pdf

Cite this

@inproceedings{683fd894cbfa4ac680e787d936d62c80,

title = "Cracking open the black box: What observations can tell us about reinforcement learning agents",

abstract = "Machine learning (ML) solutions to challenging networking problems, while promising, are hard to interpret; the uncertainty about how they would behave in untested scenarios has hindered adoption. Using a case study of an ML-based video rate adaptation model, we show that carefully applying interpretability tools and systematically exploring the model inputs can identify unwanted or anomalous behaviors of the model; hinting at a potential path towards increasing trust in ML-based solutions.",

author = "Arnaud Dethise and Marco Canini and Srikanth Kandula",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: We thank the anonymous reviewers for their feedback. We are grateful to Nikolaj Bj{\o}rner, Bernard Ghanem, Hao Wang and Xiaojin Zhu for their valuable comments and suggestions. We also thank the Pensieve authors, in particular Mohammad Alizadeh and Hongzi Mao, for their help and feedback.",

year = "2019",

month = aug,

day = "14",

doi = "10.1145/3341216.3342210",

language = "English (US)",

isbn = "9781450368728",

pages = "29--36",

booktitle = "Proceedings of the 2019 Workshop on Network Meets AI & ML - NetAI'19",

publisher = "ACM Press",

}

TY - GEN

T1 - Cracking open the black box: What observations can tell us about reinforcement learning agents

AU - Dethise, Arnaud

AU - Canini, Marco

AU - Kandula, Srikanth

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: We thank the anonymous reviewers for their feedback. We are grateful to Nikolaj Bjørner, Bernard Ghanem, Hao Wang and Xiaojin Zhu for their valuable comments and suggestions. We also thank the Pensieve authors, in particular Mohammad Alizadeh and Hongzi Mao, for their help and feedback.

PY - 2019/8/14

Y1 - 2019/8/14

N2 - Machine learning (ML) solutions to challenging networking problems, while promising, are hard to interpret; the uncertainty about how they would behave in untested scenarios has hindered adoption. Using a case study of an ML-based video rate adaptation model, we show that carefully applying interpretability tools and systematically exploring the model inputs can identify unwanted or anomalous behaviors of the model; hinting at a potential path towards increasing trust in ML-based solutions.

AB - Machine learning (ML) solutions to challenging networking problems, while promising, are hard to interpret; the uncertainty about how they would behave in untested scenarios has hindered adoption. Using a case study of an ML-based video rate adaptation model, we show that carefully applying interpretability tools and systematically exploring the model inputs can identify unwanted or anomalous behaviors of the model; hinting at a potential path towards increasing trust in ML-based solutions.

UR - http://hdl.handle.net/10754/658663

UR - http://dl.acm.org/citation.cfm?doid=3341216.3342210

UR - http://www.scopus.com/inward/record.url?scp=85072028490&partnerID=8YFLogxK

U2 - 10.1145/3341216.3342210

DO - 10.1145/3341216.3342210

M3 - Conference contribution

SN - 9781450368728

SP - 29

EP - 36

BT - Proceedings of the 2019 Workshop on Network Meets AI & ML - NetAI'19

PB - ACM Press

ER -

Cracking open the black box: What observations can tell us about reinforcement learning agents

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this