Prashan Madumal

Prashan Madumal

Researcher and Engineer

The University of Melbourne

I am a researcher in the AI and Autonomy Lab at The University of Melbourne. My research area is in Explainable AI and Reinforcement Learning. My thesis explores how actions, behaviors and decisions of sequential decision making agents (e.g. reinforcement learning agents) can be explained using causal models.

I am also a tutor and a project supervisor in the School of Computer Science and Information Systems.

Interests

  • Explainable/Interpretable Artificial Intelligence
  • Causal Learning
  • Reinforcement Learning
  • Human-Agent Interaction

Education

  • PhD in Computer Science, 2017-

    The University of Melbourne

  • BSc in Computer Science, 2016

    University of Colombo

Recent News

  • Dec 2020 - Our paper is accepted at AAAI 2021, preprint coming soon!
  • Oct 2020 - Honored to be a recipient of the Google PhD Fellowship, in recognition of my work in explainability of reinforcement learning agents. More details here.
  • Sep 2020 - I will be organzing the Explainable Agency in Artificial Intelligence Workshop at AAAI-21, together with Silvia Tulli, David Aha and Rosina Weber. See https://sites.google.com/view/xaiworkshop for more details.
  • May 2020 - I will be giving a Aribus research techtalk on explainable reinforcement learning.
  • Feb 2020 - Our paper “Explainable Reinforcement Learning Through a Causal Lens” will be presented as an oral talk at AAAI 2020
  • Feb 2020 - I’m volunteering for the Undergraduate Consortium at AAAI 2020 as a graduate mentor.
  • Feb 2020 - I was selected to participate in the Doctoral Consortium at AAAI 2020.

Publications

Improving Interpretability of CNN Models Using Non-Negative Concept Activation Vectors

Pre-print (2020)
Ruihan Zhang, Prashan Madumal, Tim Miller, Kris Ehinger, Benjamin I. P. Rubinstein
PDF

Explainable Reinforcement Learning Through a Causal Lens

Proceedings of the 34th AAAI Conference on Artificial Intelligence (2020)
Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere
PDF Proceedings

Explainable Agency in Reinforcement Learning Agents

Proceedings of the 34th AAAI Conference on Artificial Intelligence (2020)
Prashan Madumal
PDF Proceedings

Distal Explanations for Explainable Reinforcement Learning Agents

Pre-print
Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere
PDF

Designing Interactions with Intention-Aware Gaze-Enabled Artificial Agents

Human-Computer Interaction - INTERACT 2019 - 17th IFIP TC 13 International Conference (2019)
Joshua Newn, Ronal Rajneshwar Singh, Fraser Allison, Prashan Madumal, Eduardo Velloso, Frank Vetere
PDF Proceedings

Nonverbal Communication in Human-AI Interaction: Opportunities and Challenges

Human Computer Interaction and Emerging Technologies - Adjunct Proceedings from the INTERACT 2019 Workshops (2019)
Joshua Newn, Ronal Rajneshwar Singh, Fraser Allison, Prashan Madumal, Eduardo Velloso, Frank Vetere
PDF Proceedings

A Grounded Interaction Protocol for Explainable Artificial Intelligence

Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (2019)
Prashan Madumal, Tim Miller, Liz Sonenberg, Frank Vetere
PDF Proceedings

Explainable Agency in Intelligent Agents: Doctoral Consortium

Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (2019)
Prashan Madumal
PDF Proceedings

Interaction design for explainable AI: workshop proposal

Proceedings of the 30th Australian Conference on Computer-Human Interaction, OzCHI (2018)
Prashan Madumal, Ronal Rajneshwar Singh, Joshua Newn and, Frank Vetere
PDF Proceedings

Towards a Grounded Dialog Model for Explainable Artificial Intelligence

Workshop on Socio-cognitive Systems - IJCAI (2018)
Prashan Madumal, Tim Miller, Frank Vetere, Liz Sonenberg
PDF Proceedings

Adaptive event tree-based hybrid CEP computational model for Fog computing architecture

Proceedings of the 16th International Conference on Advances in ICT for Emerging Regions (ICTer) (2016)
Prashan Madumal, DAS Atukorale, TMHA Usoof
PDF Proceedings

Indoor navigation framework for mapping and localization of multiple robotic wheelchairs

5th International Conference on Intelligent Systems, Modelling and Simulation (2014)
Yasith Lokuge, Prashan Madumal, Tharindu Kumara, Naveen Ranasinghe
PDF Proceedings

Experience

 
 
 
 
 

Data Science Project Supervisor

The University of Melbourne

Mar 2020 – Present
Supervision of the capstone projects (MAST90106) that will provide the culmination of the Master of Data Science degree. It will apply the skills developed during the degree to a practical problem of relevance to science, industry, commerce or society in general.
 
 
 
 
 

Research Project Co-Supervisor

The University of Melbourne

Dec 2018 – Jul 2019

The subject COMP90055 is a research-based project, giving a capstone experience and piece of scholarship to students that is suitable as a pathway to PhD. It involves in-depth investigation of a significant problem related to Computing. The subject also provides students with skills and knowledge for analysing and solving problems, and enhanced written and oral communication skills.

Topics:

  • Deceptive Reinforcement Learning.
  • Explainable Artificial Intelligence.
 
 
 
 
 

Academic Tutor

The University of Melbourne

Jun 2018 – Present
Subjects taught - AI Planning for Autonomy (COMP90054), Machine Learning (COMP30027).
 
 
 
 
 

Software Engineer

Sysco Labs - the innovation arm of Sysco Corporation

Feb 2016 – Aug 2017
Hall of Fame 2016 winner - Hall of Fame award is awarded for the most outstanding engineering artifact of the year by Sysco Labs. Asynchronous upgrade which enables smooth system wide upgrades to the POS system was named as the winner of the 2016 Hall of fame award
 
 
 
 
 

Trainee Software Engineer

IFS

Jun 2014 – Dec 2014

Awards & Scholarships

Google PhD Fellowship

Google Aug 2020
Google PhD Fellowship students are a select group recognized by Google researchers and their institutions as some of the most promising young academics in the world. The Fellowships are awarded to students who represent the future of research - link

Google PhD Travel Scholarship

Google May 2019

AAMAS Travel Scholarship

IFAAMAS Apr 2019

Melbourne Research Scholarship

The University of Melbourne Jul 2017
Available to high-achieving students undertaking graduate research at the University of Melbourne.

Hall of Fame Award

Sysco Labs Dec 2016
Hall of Fame award is awarded for the most outstanding engineering artifact of the year by Sysco Labs.

Microsoft Imagine Cup - World Citizenship - Local Finals 1st Runners Up

Microsoft Mar 2014
The Imagine Cup World Citizenship Competition is a global contest for the best new software to address social issues.

Motorola Inter University Innovations Championship - 1st Runners Up

Motorola Dec 2013

Volunteering | Leadership

 
 
 
 
 

Secretary - Computing and Information Systems Graduate Research Students

The University of Melbourne

Jun 2019 – Jun 2020
Graduate research student body of the school of computing and information systems at the University of Melbourne.
 
 
 
 
 

Treasurer - IEEE Student Branch

University of Colombo

Jan 2015 – Jan 2016
 
 
 
 
 

Treasurer - Computer Society

University of Colombo

Jan 2015 – Jan 2016
 
 
 
 
 

Secretary - IEEE Student Branch

University of Colombo

Jan 2014 – Jan 2015
 
 
 
 
 

Microsoft Student Partner

Microsoft

Jan 2013 – Jan 2016
 
 
 
 
 

Radio Presenter

Sri Lanka Broadcasting Cooperation

Jan 2012 – Jan 2016

Contact

Write to me - pmathugama[at]student[dot]unimelb[dot]edu[dot]au