Vindula Jayawardana
vindula [AT] mit [DOT] edu
I am a PhD student in computer science at MIT.
I am fortunate to be advised by Prof. Cathy Wu
in the Electrical Engineering and Computer Science Department (EECS) and Laboratory for Information and Decision
Systems (LIDS).
Earlier, I completed my bachelors at
University of Moratuwa in Sri Lanka. I have
also spent time doing research at NVIDIA and Toyota North America, and software engineering at WSO2,
PickMe, and Trancite24.
Before graduate school, I was a part of Mobility,
Algorithms, and Society Lab at Cornell University and Data Science,
Engineering & Analytics Research Hub of University of Moratuwa.
I am broadly interested in learning-enabled autonomy, with my work spanning three main areas: (1) modeling and simulation of large-scale cyberphysical systems, (2) making learning generalize across diverse problem variations, and (3) real-world applications, particularly in autonomous driving.
In light of this, first, I leverage efficient generative models and simulation techniques to build and calibrate large-scale mulit-agent traffic systems reflecting real world conditions.
Second, I’ve developed residual reinforcement learning methods for generalizable multi-agent control. Third, I've worked on leveraging learning to control multi-agent fleets of cooperative autonomous vehicles to reduce metropolitan carbon emissions at scale. Before graduate school, I have also worked on mathematical programming for combinatorial optimizations
and natural language processing for information extraction. I also lead the project Greenwave.
[New] I'm on the job market 2024-2025. Feel free to contact me if you know of a position for which I could be a fit.
Resume  | 
Google Scholar  | 
LinkedIn  | 
Github  | 
Blog
|
|
Research
For a complete list of publications, please visit my Google
Scholar page.
|
Reinforcement Learning
Learning for Control
Combinatorial Optimizations
Intelligent Transportation Systems
Natural Language Processing
|
|
IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning
Vindula Jayawardana,
Baptiste Freydt,
Ao Qu,
Cameron Hickert,
Zhongxia Yan,
Cathy Wu
In review 2024
code |
project page |
|
|
Model-Based Transfer Learning for Contextual Reinforcement Learning
JungHoon Cho,
Vindula Jayawardana,
Sirui Li,
Cathy Wu
[NeurIPS 2024] Advances in Neural Information Processing Systems 2024
Also at European Workshop on Reinforcement Learning 2024
project page |
arXiv |
code |
OpenReview |
|
|
Mitigating Metropolitan Carbon Emissions with Dynamic Eco-driving at Scale
Vindula Jayawardana,
Baptiste Freydt,
Ao Qu,
Cameron Hickert,
Edgar Sanchez,
Catherine Tang,
Mark Tylor,
Blaine Leonard,
Cathy Wu
In review 2024
project page |
arXiv |
|
|
Generalizing Cooperative Eco-driving via Multi-residual Task Learning
Vindula Jayawardana,
Sirui Li,
Cathy Wu,
Yashar Farid,
Kentaro Oguchi
[ICRA 2024] International Conference on Robotics and Automation 2024
Also at Generalization in Planning workshop at NeurIPS 2023
Also at Machine Learning for Autonomous Driving Symposium 2023
project page |
arXiv |
poster |
slides |
video |
|
|
Learning-Augmented Vehicle Dispatching with Slack Times for High-Capacity Ride-Pooling
Youngseo Kim,
Vindula Jayawardana,
Samitha Samaranayake
[TRC 2024] Transportation Research Part C: Emerging Technologies 2024 (major revision)
arXiv |
|
|
The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning
Vindula Jayawardana,
Catherine Tang,
Sirui Li,
Dajiang Suo,
Cathy Wu
[NeurIPS 2022] Advances in Neural Information Processing Systems 2022
project page |
arXiv |
video |
poster |
slides |
|
|
Model-free Learning of Corridor Clearance: A Near-term Deployment Perspective
Vindula Jayawardana*,
Dajiang Suo*,
Cathy Wu
(* equal contribution)
[T-ITS 2023] IEEE Transactions on Intelligent Transportation Systems (T-ITS) 2023
arXiv |
|
|
Learning Eco-Driving Strategies at Signalized Intersections (MIT Homepage Spotlight)
Vindula Jayawardana,
Cathy Wu,
[ECC 2022] European Control Conference 2022
Also at Robotics for Climate Change at ICRA 2022
project page |
arXiv |
video |
poster |
slides |
|
|
Multi-behavior Learning for Socially Compatible Autonomous Driving
Sanjula Jayawardana,
Vindula Jayawardana*,
Kaneeka Vidanage,
Cathy Wu*
(* equal supervision)
[ITSC 2023] IEEE Intelligent Transportation Systems Conference 2023
paper |
poster |
|
|
The Braess Paradox in Dynamic Traffic
Dingyi Zhuang*,
Yushu Huang*,
Vindula Jayawardana,
Jinhua Zhao,
Dajiang Suo,
Cathy Wu
[ITSC 2022] IEEE Intelligent Transportation Systems Conference 2022
arXiv |
|
|
Mixed Autonomous Supervision in Traffic Signal Control
Vindula Jayawardana,
Anna Landler,
Cathy Wu
[ITSC 2021] IEEE Intelligent Transportation Systems Conference 2021
paper |
|
|
Fleet Management for Ride-Pooling with Meeting Points at Scale: A Case Study in the Five Boroughs of New York City
Motahare Mounesan,
Vindula Jayawardana,
Yaocheng Wu,
Samitha Samaranayake,
Huy T. Vo
arXiv |
code |
|
|
Word Vector Embeddings and Domain Specific Semantic-based Semi-supervised Ontology Instance Population
Vindula Jayawardana,
Dimuthu Kariyawasam,
Nisansa de Silva,
Shehan Perera
Keet Sugathadasa,
Buddhi Ayesha,
Madhavi Perera
[ICTer 2017] International Journal on Advances in ICT for Emerging Regions 2017
Seventeenth International Conference on Advances in ICT for Emerging Regions 2017
paper |
|
|
Deriving a Representative Vector for Ontology Classes with Instance Word Vector Embeddings
Vindula Jayawardana,
Dimuthu Kariyawasam,
Nisansa de Silva,
Shehan Perera
Keet Sugathadasa,
Buddhi Ayesha,
[INTECH 2017] Seventh International Conference on Innovative Computing Technology 2017
paper |
|
|
Legal Document Retrieval using Document Vector Embeddings and Deep Learning
Keet Sugathadasa,
Buddhi Ayesha,
Nisansa de Silva,
Shehan Perera
Vindula Jayawardana,
Dimuthu Kariyawasam,
Madhavi Perera
Computing Conference 2017
arXiv |
|
|
Synergistic Union of Word2vec and Lexicon for Domain Specific Semantic Similarity
Keet Sugathadasa,
Buddhi Ayesha,
Nisansa de Silva,
Shehan Perera
Vindula Jayawardana,
Dimuthu Kariyawasam,
Madhavi Perera
[ICIIS 2017] IEEE International Conference on Industrial and Information Systems 2017
paper |
|
Selected Open Source Contributions
|
Workshop Organizer
|
AVAS (RSS)
|
Conference Reviewer
|
NeurIPS, ICML, AAAI, ICRA, ITSC, NLDL, TRC30, TRB, MERCon
|
Journal Reviewer
|
T-RO, T-NNLS, T-IST, Physica A
|
Workshop Reviewer
|
CCAI (NeurIPS), WMLMDS (AAAI), R2HCAI (AAAI)
|
1.041/1.200/11.544: Transportation Systems Modeling: Teaching Assistant, MIT, Fall 2020/2021.
|
CS4622: Machine Learning: Teaching Assistant, UoM, Spring 2019.
|
CS2022: Data Structures and Algorithms: Instructor, UoM, Spring 2019.
|
CS3042: Database Systems: Teaching Assistant, UoM, Fall 2018.
|
CS2052: Computer Architecture: Teaching Assistant, UoM, Fall 2018.
|
CS2062: Object Oriented Software Development: Teaching Assistant, UoM, Spring 2018.
|
CS3962: Research and Report Writing : Teaching Assistant, UoM, Spring 2018.
|
Template adapted from 1 and 2.
|
|