Thiago D. Simão
Assistant Professor at TU/e
Office MF 7.092
MetaForum
I am an Assistant Professor in the Department of Mathematics and Computer Science at TU/e. Previously, I was a Ph.D. candidate in the Algorithmics Group at Delft University of Technology, advised by Dr. Matthijs Spaan. Next, I was a PostDoc researcher with the Department of Software Science (SWS) at Radboud University Nijmegen advised by Dr. Nils Jansen. For more details, checkout my biography or my cv .
Research Interests: The motivation for my research revolves around making AI techniques more reliable, to enable their deployment in real-world applications. I focus on developing AI algorithms for scenarios with constrained interactions with an unknown environment. I am currently interested in safe reinforcement learning, a research topic concerned with problems where a minimum performance must be guaranteed and catastrophic events must be avoided.
Academic Service:
- Organization committee of the BeNeRL Workshop 2018.
- Local organizing committee of the 28th ICAPS.
- Area Chair for NeurIPS24.
- SPC for AAMAS24.
- PC for AAAI25, ICLR24, AAAI24, NeurIPS23, ICML23, AISTATS23, ICAPS23, ICAPS23, NeurIPS22, ICML22, ICAPS22, AAAI21.
- Reviewer for JAIR, AIJ, JAAMAS, ICRA, AAAI and BRACIS.
news
2024
November
- Hiring. I am looking for a (fully paid) PhD student to work on safe RL under partial observability.
June
- Invited talk about “New Safe Practices in Reinforcement Learning” at the Belgium-Netherlands workshop on Reinforcement Learning (BeNeRL) 2024.
May
- Back to the University of Verona to teach a mini-series of lectures on designing reliable RL agents.
May
- Our paper “Scalable Safe Policy Improvement for Factored Multi-Agent MDPs” has been accepted at ICML-24.
March
- I am serving as an Area Chair for NeurIPS-24.
2023
December
- Our papers “Robust Active Measuring under Model Uncertainty” and “Factored Online Planning in Many-Agent POMDPs” have been accepted at AAAI-24.
October
- New job! I am now an assistant professor in the Data and AI cluster at Eindhoven University of Technology.
September
- The ORLEANS project on Offline Reinforcement Learning for Sustainable Transportation at Sea has received an IPR voucher.
September
- I am serving as a senior PC member for AAMAS-24.
September
- I am serving as a PC member for AAAI-24.
August
- I am serving as a PC member for ICLR-24.
August
- Invited talk at the Safe RL workshop at IJCAI 2023.
July
- Our paper “Reinforcement Learning by Guided Safe Exploration” has been accepted at ECAI-23.
May
- Our paper “Risk-aware Curriculum Generation for Heavy-tailed Task Distributions” has been accepted at UAI-23.
April
- Our paper “Scalable Safe Policy Improvement via Monte Carlo Tree Search” has been accepted at ICML-23.
April
- Our papers “Recursive Small-Step Multi-Agent A* for Dec-POMDPs” and “More for Less: Safe Policy Improvement with Stronger Performance Guarantees” have been accepted at IJCAI-23.
April
- Presenting our work on SPI in factored environments at the TiCSA 2023 workshop.
April
- Invited talk at the LiVe 2023 workshop.
March
- I am serving as a PC member for NeurIPS-23.
February
- Our paper “Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring” has been accepted at ICAPS-23.
February
- I am serving as a PC member for ICML 2023.
January
- Our paper “Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation” has been accepted at ICLR-23.
January
- I successfully defended my PhD thesis. A big thanks to my promotor team and the thesis committee.
2022
December
- Invited to teach three lectures in the Reinforcement Learning course at University of Verona.
December
- Our paper “Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking” has been accepted at ICAART-23.
November
- Our paper “Safe Policy Improvement for POMDPs via Finite-State Controllers” has been accepted at AAAI-23.
November
- Two talks at the AAAI 2022 Fall Symposium.
October
- I am serving as a PC member for AISTATS 2023.
September
- Our paper “Robust Anytime Learning of Markov Decision Processes” has been accepted at NeurIPS-22.
August
- I am serving as a PC member for ICAPS 2023.
July
- I am serving as a PC member for NeurIPS 2022.
June
- Our paper “Safety-constrained reinforcement learning with a distributional safety critic” has been published at Machine Learning.
May
- Two papers presented at the ALA 2022 workshop on Safe Transfer in RL and Solving Hidden Parameter MDPs with Hindsight.
April
- Invited talk for the Oden Institute seminar at UT Austin.
April
- Talk at the LiVe-22 workshop about Safe Transfer in Reinforcement Learning.
March
- Talk at the ADML meetup about Ensuring Safety for Reinforcement Learning.
January
- I am serving as a PC member for ICML 2022.
2021
December
- Talk at the iVerif workshop on Safety Abstractions.
October
- I am serving as a PC member for the Planning and Learning track at ICAPS 2022.
August
- Talk at the PRL workshop.
August
- At ICAPS-21 attending the mentoring program.
June
- Invited talk at the Center for Artificial Intelligence.
May
- At AAMAS-21 presenting the AlwaysSafe paper.
March
- Talk at the LiVe-21 workshop about AlwaysSafe.
March
- Guest lecture on Safe RL at the Algorithms for Intelligent Decision Making course.
February
- Invited talk at the SWS-seminar about our AAMAS paper.
2020
December
- Our paper “AlwaysSafe: Reinforcement Learning Without Safety Constraint Violations During Training” has been accepted at AAMAS-21.
December
- Our paper “WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning” has been accepted at AAAI-21.
September
- I am serving as a PC member for AAAI-21.
May
- At AAMAS-20 presenting the paper “Safe Policy Improvement with an Estimated Baseline Policy.”
May
- Released gym-factored, a collection of factored environments that are OpenAI Gym compliant.
2019
August
- At IJCAI-19 presenting our paper on structure learning for safe RL.
August
- At IJCAI-19 participating on the doctoral consortium .
May
- Attending the conference RLDM-19.
May
- Starting my interniship at MSR Montreal with Romain Laroche and Remi Tachet des Combes.
May
- I got the prize for Best Poster in our department’s poster session.
March
- In Hilversum, presenting our work on reinforcement learning at the ICT.Open-19.
January
- At AAAI-19 presenting our paper on safe policy improvement in factored environments.
2018
November
- I am co-organizing the Belgium Netherlands Workshop on Reinforcement Learning (BeNeRL-18).
October
- I am attending the 14th European Workshop on Reinforcement Learning (EWRL-18).
July
- I gave a contributed talk at the ICML-18 Workshop on Planning and Learning.
June
- I presented a poster at ICAPS-18.
June
- I am helping the local organizing committee of the ICAPS-18 at Delft.
June
- Attending the ICAPS-18 summer school at Noordwijk.
2017
November
- I presented a poster at the Energy Event promoted by the PowerWeb Institute.
October
- Presenting a poster at the EEMCS’s PhD Event.
October
- I attended the ACAI Summer School on Reinforcement Learning.
August
- I attended the 19th European Agent Systems Summer School.