Tristan Tomilin

About

Tristan Tomilin, PhD Candidate and AI Researcher

Tristan Tomilin

  • CV: [PDF]
  • Email: t.tomilin@tue.nl
  • City: Eindhoven, The Netherlands

I am a PhD candidate at the Technical University of Eindhoven advised by Mykola Pechenizkiy and Meng Fang. My research interests span across several domains of Reinforcement Learning, including continual learning, multi-agent systems, and safe RL. Central to my work is the pursuit of creating more robust, reliable, and meaningful simulation environments that enhance the development and evaluation of AI systems.

News

Mar 2025 Served as a reviewer for ICML 2025.
Jan 2025 Paper accepted at ICLR 2025: HASARD.
Jan 2025 Presented HASARD to the Sequential Decision Making group at TU Delft.
Dec 2024 Presented HASARD in the RLChina online seminar. Watch on BiliBili
Oct 2024 Presented my research to the UoE Agents online RL Reading Group at the University of Edinburgh. Watch on YouTube
Oct 2024 Served as a reviewer for ICLR 2025.
Jul 2024 Attended the DLRL 2024 Summer School.
Jun 2024 Served as a reviewer for NeurIPS 2024.
Jun 2024 Presented my research to Prof. Ling Chen's group during my research visit at the University of Technology Sydney.
May 2024 Attended AAMAS 2024.
Apr 2024 Presented my research to Prof. Aske Plaat's group at Leiden University.
Mar 2024 Paper accepted at ICLR 2024 GenAI4DM Workshop: SMALL.
Dec 2023 Paper accepted at AAMAS 2024: MaDi.
Dec 2023 Attended NeurIPS 2023.
Nov 2023 Presented COOM to Prof. Tianyi Zhou's group during my research visit at the University of Maryland.
Sep 2023 Paper accepted at NeurIPS 2023: COOM. Watch a short presentation
Jul 2023 Attended the ESSAI 2023 Summer School.
Apr 2022 Paper accepted at CoG 2022: LevDoom.

Publications

HASARD: A Benchmark for Embodied Safe Reinforcement Learning

Tristan Tomilin, Meng Fang, Mykola Pechenizkiy

Proceedings of the 13th International Conference on Learning Representations (ICLR 2025)

MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning

Bram Grooten, Tristan Tomilin, Gautham Vasan, Matthew E. Taylor, A. Rupam Mahmood, Meng Fang, Mykola Pechenizkiy, Decebal Constantin Mocanu

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024)

Safe Multi-agent Reinforcement Learning with Natural Language Constraints

Ziyan Wang, Meng Fang, Tristan Tomilin, Fei Fang, Yali Du

Proceedings of the GenAI4DM Workshop at the 12th International Conference on Learning Representations (ICLR 2024)

COOM: A Game Benchmark for Continual Reinforcement Learning

Tristan Tomilin, Meng Fang, Yudi Zhang, Mykola Pechenizkiy

Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023), Datasets and Benchmarks Track

LevDoom: A Benchmark for Generalization on Level Difficulty in Reinforcement Learning

Tristan Tomilin, Tianhong Dai, Meng Fang, Mykola Pechenizkiy

Proceedings of the 2022 IEEE Conference on Games (CoG 2022)

Resume

Education

PhD in Deep Reinforcement Learning

11/2021 - Present

Eindhoven University of Technology, Eindhoven, The Netherlands

Supervisors: Prof. Meng Fang and Prof. Mykola Pechenizkiy

MSc in Data Science in Engineering

09/2019 - 08/2021

Eindhoven University of Technology, Eindhoven, The Netherlands

Title: GViZDoom: A Benchmark for Generalization of FPS Games in Deep Reinforcement Learning

BSc in Information Technology, Informatics

09/2013 - 06/2016

Tallinn University of Technology, Tallinn, Estonia

Professional Experience

PhD Researcher

11/2021 - Present

Eindhoven University of Technology, Eindhoven, The Netherlands

Machine Learning Engineer

04/2021 - 11/2021

Awaves B.V., Enschede, The Netherlands

Data Scientist

02/2021 - 04/2021

OpenML, Eindhoven, The Netherlands

Full-Stack Developer

04/2019 - 09/2019

Nortal AS, Tallinn, Estonia

Software Developer

10/2017 - 04/2019

Ardera OÜ, Tallinn, Estonia

Software Engineer

06/2015 - 11/2018

SEB Pank AS, Tallinn, Estonia

Contact

Location

Eindhoven, The Netherlands

Email

t.tomilin@tue.nl