Generating Reinforcement Learning Environments for Industrial Communication Protocols

Akos Csiszar; Viktor Krimstein; Justus Bogner; Alexander Verl

doi:10.1109/AI4I51902.2021.00022

Generating Reinforcement Learning Environments for Industrial Communication Protocols

Akos Csiszar, Viktor Krimstein, Justus Bogner, Alexander Verl

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

An important part of any reinforcement learning application is interfacing the agent to its environment. To enable an easier use of reinforcement learning agents in manufacturing and automation-related real-world environments, we propose an environment generator which acts as an adapter between the interface of the agent and existing industrial communication protocols. This paper describes the functionality and architecture of such an environment generator.

Original language	English
Title of host publication	Proceedings - 2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	57-60
ISBN (Electronic)	9781665434102
DOIs	https://doi.org/10.1109/AI4I51902.2021.00022
Publication status	Published - 2021
Externally published	Yes
Event	4th International Conference on Artificial Intelligence for Industries, AI4I 2021 - Virtual, Online, United States Duration: 20 Sept 2021 → 22 Sept 2021

Conference

Conference	4th International Conference on Artificial Intelligence for Industries, AI4I 2021
Country/Territory	United States
City	Virtual, Online
Period	20/09/21 → 22/09/21

Funding

We thank the Federal Ministry for Economic Affairs and Energy (BMWi) for providing funding for this work through the project FabOS (Reference number 01MK20010D).

Funders	Funder number
Bundesministerium für Wirtschaft und Energie	01MK20010D

Access to Document

10.1109/AI4I51902.2021.00022

Persistent URL (handle)

Persistent link

Cite this

@inproceedings{6359224f2bdc4760b35203265b25e6ec,

title = "Generating Reinforcement Learning Environments for Industrial Communication Protocols",

abstract = "An important part of any reinforcement learning application is interfacing the agent to its environment. To enable an easier use of reinforcement learning agents in manufacturing and automation-related real-world environments, we propose an environment generator which acts as an adapter between the interface of the agent and existing industrial communication protocols. This paper describes the functionality and architecture of such an environment generator.",

author = "Akos Csiszar and Viktor Krimstein and Justus Bogner and Alexander Verl",

year = "2021",

doi = "10.1109/AI4I51902.2021.00022",

language = "English",

pages = "57--60",

booktitle = "Proceedings - 2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "4th International Conference on Artificial Intelligence for Industries, AI4I 2021 ; Conference date: 20-09-2021 Through 22-09-2021",

}

Csiszar, A, Krimstein, V, Bogner, J & Verl, A 2021, Generating Reinforcement Learning Environments for Industrial Communication Protocols. in Proceedings - 2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021. Institute of Electrical and Electronics Engineers Inc., pp. 57-60, 4th International Conference on Artificial Intelligence for Industries, AI4I 2021, Virtual, Online, United States, 20/09/21. https://doi.org/10.1109/AI4I51902.2021.00022

Generating Reinforcement Learning Environments for Industrial Communication Protocols. / Csiszar, Akos; Krimstein, Viktor; Bogner, Justus et al.
Proceedings - 2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 57-60.

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Generating Reinforcement Learning Environments for Industrial Communication Protocols

AU - Csiszar, Akos

AU - Krimstein, Viktor

AU - Bogner, Justus

AU - Verl, Alexander

PY - 2021

Y1 - 2021

N2 - An important part of any reinforcement learning application is interfacing the agent to its environment. To enable an easier use of reinforcement learning agents in manufacturing and automation-related real-world environments, we propose an environment generator which acts as an adapter between the interface of the agent and existing industrial communication protocols. This paper describes the functionality and architecture of such an environment generator.

AB - An important part of any reinforcement learning application is interfacing the agent to its environment. To enable an easier use of reinforcement learning agents in manufacturing and automation-related real-world environments, we propose an environment generator which acts as an adapter between the interface of the agent and existing industrial communication protocols. This paper describes the functionality and architecture of such an environment generator.

UR - http://www.scopus.com/inward/record.url?scp=85125994851&partnerID=8YFLogxK

U2 - 10.1109/AI4I51902.2021.00022

DO - 10.1109/AI4I51902.2021.00022

M3 - Conference contribution

SP - 57

EP - 60

BT - Proceedings - 2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 4th International Conference on Artificial Intelligence for Industries, AI4I 2021

Y2 - 20 September 2021 through 22 September 2021

ER -

Generating Reinforcement Learning Environments for Industrial Communication Protocols

Abstract

Conference

Funding

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this