Thiago D. Simão

Assistant Professor at TU/e

portrait.jpg

Office MF 4.120

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 :mega:

2024

June

May

May

March

2023

December

October

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

July

May

April

April

April

April

March

February

February

January

January

  • I successfully defended my PhD thesis. A big thanks to my promotor team and the thesis committee. :mortar_board:

2022

December

December

November

November

October

September

August

July

June

May

April

April

March

  • Talk at the ADML meetup about Ensuring Safety for Reinforcement Learning.

January

2021

December

October

August

August

June

May

March

March

  • Guest lecture on Safe RL at the Algorithms for Intelligent Decision Making course.

February

2020

December

December

September

  • I am serving as a PC member for AAAI-21.

May

May

  • Released gym-factored, a collection of factored environments that are OpenAI Gym compliant.

2019

August

August

May

  • Attending the conference RLDM-19.

May

May

  • I got the prize for Best Poster in our department’s poster session. :trophy:

March

  • In Hilversum, presenting our work on reinforcement learning at the ICT.Open-19.

January

2018

November

October

July

June

June

  • I am helping the local organizing committee of the ICAPS-18 at Delft. :netherlands:

June

2017

November

October

  • Presenting a poster at the EEMCS’s PhD Event.

October

August

selected publications

  1. Safe Policy Improvement for POMDPs via Finite-State Controllers
    Simão, Thiago D.Suilen, Marnix, and Jansen, Nils
    In Proceedings of the AAAI Conference on Artificial Intelligence 2023
  2. AlwaysSafe: Reinforcement Learning Without Safety Constraint Violations During Training
    Simão, Thiago D.Jansen, Nils, and Spaan, Matthijs T. J.
    In Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS) 2021
  3. Safe Policy Improvement with Baseline Bootstrapping in Factored Environments
    Simão, Thiago D., and Spaan, Matthijs T. J.
    In Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence 2019