demonstration

Towers of Saliency: A Reinforcement Learning Visualization Using Immersive Environments

Authors:

Nathan Douglas,

Dianna Yim,

Bilal Kartal,

Pablo Hernandez-Leal,

Frank Maurer,

Matthew E. TaylorAuthors Info & Claims

ISS '19: Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces

Pages 339 - 342

https://doi.org/10.1145/3343055.3360747

Published: 10 November 2019 Publication History

Get Access

Abstract

Deep reinforcement learning (DRL) has had many successes on complex tasks, but is typically considered a black box. Opening this black box would enable better understanding and trust of the model which can be helpful for researchers and end users to better interact with the learner. In this paper, we propose a new visualization to better analyze DRL agents and present a case study using the Pommerman benchmark domain. This visualization combines two previously proven methods for improving human understanding of systems: saliency mapping and immersive visualization.

Supplementary Material

MP4 File (issde13.mp4)

Supplemental video

Download
91.72 MB

References

[1]

A. Adadi and M. Berrada. 2018. Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI). IEEE Access 6 (2018), 52138--52160. http://dx.doi.org/10.1109/ACCESS.2018.2870052

Crossref

Google Scholar

[2]

Sam Greydanus, Anurag Koul, Jonathan Dodge, and Alan Fern. 2017. Visualizing and Understanding Atari Agents. CoRR abs/1711.00138 (2017). http://arxiv.org/abs/1711.00138

Google Scholar

[3]

L. Itti, C. Koch, and E. Niebur. 1998. A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 11 (Nov 1998), 1254--1259. http://dx.doi.org/10.1109/34.730558

Digital Library

Google Scholar

[4]

O. Kwon, C. Muelder, K. Lee, and K. Ma. 2016. A Study of Layout, Rendering, and Interaction Methods for Immersive Graph Visualization. IEEE Transactions on Visualization and Computer Graphics 22, 7 (July 2016), 1802--1815. http://dx.doi.org/10.1109/TVCG.2016.2520921

Digital Library

Google Scholar

[5]

Volodymyr Mnih, Adrià Puigdomè nech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. CoRR abs/1602.01783 (2016). http://arxiv.org/abs/1602.01783

Google Scholar

[6]

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. 2015. Human-level control through deep reinforcement learning. Nature 518 (25 Feb 2015), 529 EP --. https://doi.org/10.1038/nature14236

Crossref

Google Scholar

[7]

Cinjon Resnick, Wes Eldridge, David Ha, Denny Britz, Jakob Foerster, Julian Togelius, Kyunghyun Cho, and Joan Bruna. 2018. Pommerman: A Multi-Agent Playground. CoRR abs/1809.07124 (2018). http://arxiv.org/abs/1809.07124

Google Scholar

[8]

G. K. L. Tam, V. Kothari, and M. Chen. 2017. An Analysis of Machine- and Human-Analytics in Classification. IEEE Transactions on Visualization and Computer Graphics 23, 1 (Jan 2017), 71--80. http://dx.doi.org/10.1109/TVCG.2016.2598829

Digital Library

Google Scholar

[9]

W. Usher, P. Klacansky, F. Federer, P. Bremer, A. Knoll, J. Yarch, A. Angelucci, and V. Pascucci. 2018. A Virtual Reality Visualization Tool for Neuron Tracing. IEEE Transactions on Visualization and Computer Graphics 24, 1 (Jan 2018), 994--1003. http://dx.doi.org/10.1109/TVCG.2017.2744079

Crossref

Google Scholar

[10]

J. Wang, L. Gou, H. Shen, and H. Yang. 2019. DQNViz: A Visual Analytics Approach to Understand Deep Q-Networks. IEEE Transactions on Visualization and Computer Graphics 25, 1 (Jan 2019), 288--298. http://dx.doi.org/10.1109/TVCG.2018.2864504

Digital Library

Google Scholar

Cited By

View all

Meyer LZhu J(2024)Slide to Explore 'What If': An Analysis of Explainable InterfacesAdjunct Proceedings of the 2024 Nordic Conference on Human-Computer Interaction10.1145/3677045.3685416(1-6)Online publication date: 13-Oct-2024
https://dl.acm.org/doi/10.1145/3677045.3685416
Schulz TLiu SMädche AWeinhardt C(2024)Enhancing AI Education for Business Students through Extended Reality: An Exploratory StudyProceedings of Mensch und Computer 202410.1145/3670653.3677506(599-604)Online publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1145/3670653.3677506
Dissanayaka DWanasinghe TGosine R(2024)Explainable Artificial intelligence for Autonomous UAV Navigation2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)10.1109/IROS58592.2024.10801529(10439-10446)Online publication date: 14-Oct-2024
https://doi.org/10.1109/IROS58592.2024.10801529
Show More Cited By

Index Terms

Towers of Saliency: A Reinforcement Learning Visualization Using Immersive Environments
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Neural networks
2. Human-centered computing
  1. Human computer interaction (HCI)
    1. Interaction paradigms
      1. Virtual reality
  2. Visualization
    1. Visualization techniques
      1. Heat maps

Recommendations

Designing Spatial Visualization and Interactions of Immersive Sankey Diagram in Virtual Reality
MM '24: Proceedings of the 32nd ACM International Conference on Multimedia

Virtual reality (VR) is a revolutionary method of presenting data visualizations, which brings potential possibilities for enhancing analytical activities. However, applying this method to visualize complex data flows remains largely underexplored, ...
Introduction to IATK: An Immersive Visual Analytics toolkit
ISS '19: Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces

Immersive Analytics is an emerging interdisciplinary research area that investigates the use of nontraditional display and input technology to immerse users in their data. A prominent aspect this research investigates is "immersive data visualization", ...
Building a Prototype for Easy to Use Collaborative Immersive Analytics
Computational Science – ICCS 2021
Abstract
The increase in the size and complexity of today’s datasets creates a need to develop and experiment with novel data visualization methods. One of these innovations is immersive analytics, in which extended reality technologies such as virtual ...

Comments

Information & Contributors

Information

Published In

ISS '19: Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces

November 2019

450 pages

ISBN:9781450368919

DOI:10.1145/3343055

General Chairs:
Bongshin Lee
Microsoft Research, USA
,
Geehyuk Lee
KAIST, South Korea
,
Program Chairs:
Stacey Scott
University of Guelph, Canada
,
Melanie Tory
Tableau Software, USA
,
Jeonghyun Kim
Korea University, South Korea

Permission to make digital or hard copies of part or all 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 third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 10 November 2019

Check for updates

Author Tags

Qualifiers

Demonstration

Funding Sources

Natural Sciences and Engineering Research Council of Canada

Conference

ISS '19

Sponsor:

SIGCHI

ISS '19: Interactive Surfaces and Spaces

November 10 - 13, 2019

Daejeon, Republic of Korea

Acceptance Rates

ISS '19 Paper Acceptance Rate 26 of 85 submissions, 31%;

Overall Acceptance Rate 147 of 533 submissions, 28%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
313
Total Downloads

Downloads (Last 12 months)24
Downloads (Last 6 weeks)0

Reflects downloads up to 28 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Meyer LZhu J(2024)Slide to Explore 'What If': An Analysis of Explainable InterfacesAdjunct Proceedings of the 2024 Nordic Conference on Human-Computer Interaction10.1145/3677045.3685416(1-6)Online publication date: 13-Oct-2024
https://dl.acm.org/doi/10.1145/3677045.3685416
Schulz TLiu SMädche AWeinhardt C(2024)Enhancing AI Education for Business Students through Extended Reality: An Exploratory StudyProceedings of Mensch und Computer 202410.1145/3670653.3677506(599-604)Online publication date: 1-Sep-2024
https://dl.acm.org/doi/10.1145/3670653.3677506
Dissanayaka DWanasinghe TGosine R(2024)Explainable Artificial intelligence for Autonomous UAV Navigation2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)10.1109/IROS58592.2024.10801529(10439-10446)Online publication date: 14-Oct-2024
https://doi.org/10.1109/IROS58592.2024.10801529
Çetin EBarrado CSalamí EPastor E(2024)Analyzing deep reinforcement learning model decisions with Shapley additive explanations for counter drone operationsApplied Intelligence10.1007/s10489-024-05733-254:23(12095-12111)Online publication date: 10-Sep-2024
https://doi.org/10.1007/s10489-024-05733-2
Hickling TZenati AAouf NSpencer P(2023)Explainability in Deep Reinforcement Learning, a Review into Current Methods and ApplicationsACM Computing Surveys10.1145/3623377Online publication date: 1-Nov-2023
https://dl.acm.org/doi/10.1145/3623377
Çetin EBarrado CPastor E(2023)Explainability of Deep Reinforcement Learning Method with Drones2023 IEEE/AIAA 42nd Digital Avionics Systems Conference (DASC)10.1109/DASC58513.2023.10311156(1-9)Online publication date: 1-Oct-2023
https://doi.org/10.1109/DASC58513.2023.10311156
Agrawal AMcComb C(2022)Comparing Strategies for Visualizing the High-Dimensional Exploration Behavior of CPS Design Agents2022 IEEE Workshop on Design Automation for CPS and IoT (DESTION)10.1109/DESTION56136.2022.00017(64-69)Online publication date: May-2022
https://doi.org/10.1109/DESTION56136.2022.00017
Chromik MButz A(2021)Human-XAI Interaction: A Review and Design Principles for Explanation User InterfacesHuman-Computer Interaction – INTERACT 202110.1007/978-3-030-85616-8_36(619-640)Online publication date: 30-Aug-2021
https://dl.acm.org/doi/10.1007/978-3-030-85616-8_36
Lawton BSloan HAbou Gharib PMaurer FGuarido de Andrade MFathalian ATrad DJorge JFerreira AMarquardt NChevalier F(2020)SIERA: The Seismic Information Extended Reality Analytics ToolCompanion Proceedings of the 2020 Conference on Interactive Surfaces and Spaces10.1145/3380867.3426223(73-77)Online publication date: 8-Nov-2020
https://dl.acm.org/doi/10.1145/3380867.3426223
Agarwal SWallner GBeck F(2020)Bombalytics: Visualization of Competition and Collaboration Strategies of Players in a Bomb Laying GameComputer Graphics Forum10.1111/cgf.1396539:3(89-100)Online publication date: 18-Jul-2020
https://doi.org/10.1111/cgf.13965
Show More Cited By

View Options

Login options

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

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Abstract

Supplementary Material

References

Cited By

Index Terms

Recommendations

Designing Spatial Visualization and Interactions of Immersive Sankey Diagram in Virtual Reality

Introduction to IATK: An Immersive Visual Analytics toolkit

Building a Prototype for Easy to Use Collaborative Immersive Analytics

Comments

Information

Published In

Sponsors

Publisher

Publication History

Check for updates

Author Tags

Qualifiers

Funding Sources

Conference

Acceptance Rates

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

Login options

Full Access

View options

PDF

eReader

Share

Share this Publication link

Share on social media

Affiliations