short-paper

Engineering a platform for reinforcement learning workloads

Authors:

Ali Kanso,

Kinshuman PatraAuthors Info & Claims

CAIN '22: Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI

Pages 88 - 89

https://doi.org/10.1145/3522664.3528609

Published: 17 October 2022 Publication History

Get Access

Abstract

Reinforcement Learning (RL) is an area of machine learning concerned with teaching intelligent agents to take desired actions in a specific environment. The teaching part can be performed in a simulated environment where the agent can learn how to react to the (simulated) current state in order to reach a desired state. Offering Reinforcement Learning as a service with stringent reliability and scalability requirements, entails a set of challenges at both the architectural and implementation level. In this paper we present the Bonsai platform for RL workloads. We discuss the requirements, design and implementation of the Bonsai platform.

References

[1]

Richard S. Sutton and Andrew G. Barto Reinforcement Learning: An Introduction, MIT press, Cambridge, MA, 2018

Google Scholar

[2]

Bonsai Platform, URL: https://www.microsoft.com/en-us/ai/autonomous-systems-project-bonsai, accessed in January 2022.

Google Scholar

[3]

Inkling DSL language, URL: https://docs.microsoft.com/en-us/bonsai/inkling/basics, accessed in January 2022.

Google Scholar

[4]

Azure AKS, URL: https://azure.microsoft.com/en-us/overview/kubernetes-on-azure, accessed in January 2022.

Google Scholar

[5]

Azure Container Instances, URL: https://azure.microsoft.com/en-us/services/container-instances, accessed in January 2022.

Google Scholar

[6]

The Four Pillars of High Availability, URL: https://alikanso.medium.com/the-four-pillars-of-high-availability-d41c1609e0ba, accessed in January 2022.

Google Scholar

Index Terms

Engineering a platform for reinforcement learning workloads
1. Software and its engineering
  1. Software organization and properties
    1. Software system structures

Recommendations

Reward Shaping in Episodic Reinforcement Learning
AAMAS '17: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems

Recent advancements in reinforcement learning confirm that reinforcement learning techniques can solve large scale problems leading to high quality autonomous decision making. It is a matter of time until we will see large scale applications of ...
Using Transfer Learning to Speed-Up Reinforcement Learning: A Cased-Based Approach
LARS '10: Proceedings of the 2010 Latin American Robotics Symposium and Intelligent Robotics Meeting

Reinforcement Learning (RL) is a well-known technique for the solution of problems where agents need to act with success in an unknown environment, learning through trial and error. However, this technique is not efficient enough to be used in ...
The role of Reinforcement Learning in software testing
Abstract Context:
Software testing is applied to validate the behavior of the software system and identify flaws and bugs. Different machine learning technique types such as supervised and unsupervised learning were utilized in software testing. However, ...

Comments

Information & Contributors

Information

Published In

CAIN '22: Proceedings of the 1st International Conference on AI Engineering: Software Engineering for AI

May 2022

254 pages

ISBN:9781450392754

DOI:10.1145/3522664

General Chair:
Ivica Crnkovic
Chalmers University of Technology, SE

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

IEEE TCSC: IEEE Technical Committee on Scalable Computing

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 October 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Conference

CAIN '22

Sponsor:

SIGSOFT

CAIN '22: 1st Conference on AI Engineering - Software Engineering for AI

May 16 - 24, 2022

Pennsylvania, Pittsburgh

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
38
Total Downloads

Downloads (Last 12 months)8
Downloads (Last 6 weeks)0

Reflects downloads up to 17 Oct 2024

Other Metrics

View Author Metrics

Citations

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Index Terms

Recommendations

Reward Shaping in Episodic Reinforcement Learning

Using Transfer Learning to Speed-Up Reinforcement Learning: A Cased-Based Approach

The role of Reinforcement Learning in software testing