symp
Symp
Machine Learning Reinforcement Learning Autonomous Systems

Ashwin Devanga

Last Updated: Jan 2026

About Me

symp

Ashwin Devanga is a Computer Science PhD student at the University of North Dakota, working under the supervision of Dr. Tingjun Lei. He worked as a Software Engineer in test for MATLAB Math, Data Analysis and Mathematical Modeling at Mathworks, in Natick, MA until October 2024. Prior to working for MathWorks, Ashwin completed his Masters degree in Data Analytics Engineering (MS) at Northeastern University, Boston MA in 2022. He also holds a Degree in Biotechnology Engineering (B.Tech) from Indian Institute of Technology Guwahati, Guwahati, India.
Ashwin's primary field of research is Reinforcement Learning (RL). He has contributed to both theoretical RL and its optimization for on-shot learning. Ashwin served as a research assistant for Prof. K Yamauchi at Chubu University, Japan, during the summers of 2018 and 2019. His work from these internships was published as a research paper at the International Conference on Pattern Recognition Applications and Methods (ICPRAM) 2019, held in Prague, Czech Republic. Ashwin worked under Prof Dehghani while pursuing his Master's degree, working in the field of applied RL for industrial Simulations and Operations Research (OR) problems. His work included the use of multiple tools/languages such as Simio, Python and C# - Simio to build the multiple industry level simulation models, Python to build RL models and C# APIs to link the two.
Currently working on RL methods for Autonomous systems such as UAVs and AUVs, Ashwin is also a teaching assistant for several courses at UND.
Ashwin is proficient in multiple programming languages, including Python, R, MATLAB, Java, C, and C#, and has extensive experience with tools like Tableau, Git, Make, CMake, LaTeX, and Simio. Outside of academics, Ashwin is passionate about outdoor activities, constantly searching for his next adventure. He enjoys snowboarding during the winters but loves hiking, camping, fishing and kitesurfing during the warmer months.

  • Name

    Ashwin Devanga

  • Current Location

    Grand Forks, ND

  • Website

    ashwindevanga.com

  • Hometown

    Bangalore, India

Download My Resume here

5

Papers Published

4

Papers in Progress

7

Number of Citations

2

Years of Professional Experience

Papers

Devanga, A. and Yamauchi, K. (2019).
Learning of Human and Computer: Supervised Actor-Critic based Collaboration Scheme.
In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
ISBN 978-989-758-351-3, pages 794-801. DOI: 10.5220/0007568407940801

ICPRAM 2019

Yamauchi Labo, Chubu University, Japan

若原 涼, Ashwin Devanga, and 山内康一郎 (2019).
人と機械学習の協調による未知問題の解の探索法.
In The Proceedings of the 29th Annual Conference of Japanese Neural Network Society.
JNNS2019P2-69

JNNS 2019

Yamauchi Labo, Chubu University, Japan

Ashwin Devanga, Emily Diaz Badilla and Mohammad Dehghanimohammadabadi.
Applied Reinforcement Learning for Decision Making in Industrial Simulation Environments.
2022 Winter Simulation Conference (WSC), Singapore, 2022
pp. 2819-2829, DOI: 10.1109/WSC57314.2022.10015282.

WSC 2022

Prof. Dehghanimohammadabadi's Lab, Northeastern University

Sahil Belsare, Ashwin Devanga, and Mohammad Dehghanimohammadabadi
AI-DRIVEN MULTI-OBJECTIVE UAV ROUTE OPTIMIZATION
2024 Winter Simulation Conference (WSC), Orlando, FL, USA, 2024
pp. 2619-2630, DOI: 10.1109/WSC63780.2024.10838909

WSC 2024

Prof. Dehghanimohammadabadi's Lab, Northeastern University

Ashwin Devanga and Mohammad Dehghanimohammadabadi
DM-Gym: A Reinforcement Learning Python Library for Data Mining Problems
Masters Thesis

Northeastern Libraries 2022

Prof. Dehghanimohammadabadi's Lab, Northeastern University

Ashwin Devanga, Tingjun Lei, Jueming Hu, Jun Chen and Chaomin Luo
Trustworthy Cyber-Resilient Reinforcement Learning for Secure Navigation under Adversarial Attack
Cyber Awareness and Research Symposium (CARS), Grand Forks, ND, USA, 2025
pp 1-6. DOI: 10.1109/CARS67163.2025.11337781

IEEE CARS 2025

Prof. Tingjun Lei's Lab, University of North Dakota

Ashwin Devanga, Tingjun Lei, Jueming Hu, Chaomin Luo and Sicong Shao
Deep Reinforcement Learning for USV Navigation in Dynamic Ocean Environments
IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO), Chengdu, China, 2025
Published

IEEE ROBIO 2025

Prof. Tingjun Lei's Lab, University of North Dakota

My Resume

  • Education

  • 2025-Present

    PhD

    University of North Dakota, Grand Forks

    PhD in Computer Science, Under Dr. Tingjun Lei, from the School of Electrical Engineering and Computer Science (SEECS), College of Engineering and Mines, University of North Dakota (UND).

  • 2020-2022

    Masters Degree

    Northeastern University, Boston

    Master of Science (MS) in Data Analytics Engineering (DAE), from the department of Mechanical and Industrial Engineering (MIE), College of Engineering(COE), Northeastern University (NEU)

  • 2016-2020

    Bachelors Degree

    Indian Institute of Technology Guwahati, Guwahati

    Bachelors (B.Tech) in Biotechnology, from the department of Biosciences and Bioengineering(BSBE), Indian Institute of Technology Guwahati (IITG)

  • Experience

  • 2025-Present

    Graduate Teaching Assistant

    University of North Dakota

    I am a part-time teaching assistant for undergraduate computer science courses at UND. I am a TA for Secure Software Engineering, Object Oriented Programming and Digital Circuits Laboratory.

  • 2022-2024

    Software Engineer in Test

    Mathworks

    Worked in Quality Engineering supporting the core math and data analysis teams by prototyping functions, designing and writing tests, and fixing any bugs found in these areas.

  • 2021-2022

    Research Assistant

    Northeastern University

    Worked on using Reinforcement Learning (RL) to solve optimisation problems in industry. Operations Rsearch (OR) problems such as Vehicle Routing Problem (VRP) and Job Scheduling were the major problem statements.

  • 2021-2022

    Teaching Assistant

    Northeastern University

    Reinforcement Learning: 4 Semesters
    MetaHeuristics and Applications: 4 Semesters
    Simulation Modeling and Analysis: 4 Semesters

  • 2018 and 2019

    Research Assistant

    Chubu University, Japan

    Worked on Research Projects related to Reinforcement Learning (RL) algorithms and their optimisation for one-shot learning.

My Hobbies

Travelling

Snowboarding

Coding

Music

Hiking

Kitesurfing

My Skills

Python

100%

R

75%

MATLAB

100%

WebDev Tools

70%

Tableau

70%

C

85%

Java

75%

SQL

70%
Download My Resume here Download a short version of my resume here

Projects and Publications

Papers published, Posters presented and Talks given by me at Conferences and Journals till date. My Google Scholar Page

symp

Deep Reinforcement Learning for USV Navigation in Dynamic Ocean Environments

symp

Trustworthy Cyber-Resilient Reinforcement Learning for Secure Navigation under Adversarial Attack

symp

AI-Driven Multi-Objective UAV Route Optimization

symp

DM-Gym

symp

Applied Reinforcement Learning for Decision Making in Industrial Simulation Environments

symp

Collaborative Learning of Human and Computer: Supervised Actor-Critic based Collaboration Scheme

My Blog

This is my blog where my thoughts live. Check it out here at blog.ashwindevanga.com







Contact Me

If you need any help, have any available oportunities or just want to say hi, feel free to shoot me a message.
If you face any errors please feel free to email me at ashwindevanga@live.com