Thiago D. Simão
PostDoc researcher at Radboud University Nijmegen
I am Thiago. Currently, I am a PostDoc researcher with the Department of Software Science (SWS) at Radboud University Nijmegen advised by Dr. Nils Jansen. Previously, I was a Ph.D. candidate in the Algorithmics Group at Delft University of Technology, advised by Dr. Matthijs Spaan. 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.
- Organization committee of the BeNeRL Workshop 2018.
- Local organizing committee of the 28th ICAPS.
- PC for NeurIPS22, ICML22, ICAPS22, AAAI21.
- Reviewer for JAAMAS, ICRA, AAAI and BRACIS.
Besides my professional activities, I like to run, play boardgames, listen to music and read.
- Our paper “Risk-aware Curriculum Generation for Heavy-tailed Task Distributions” has been accepted at UAI-23.
- Our paper “Scalable Safe Policy Improvement via Monte Carlo Tree Search” has been accepted at ICML-23.
- 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.
- Presenting our work on SPI in factored environments at the TiCSA 2023 workshop.
- Invited talk at the LiVe 2023 workshop.
- Our paper “Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring” has been accepted at ICAPS-23.
- I am serving as a PC member for ICML 2023.
- Our paper “Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation” has been accepted at ICLR-23.
- I successfully defended my PhD thesis. A big thanks to my promotor team and the thesis committee.
- Invited to teach three lectures in the Reinforcement Learning course at University of Verona.
- Our paper “Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking” has been accepted at ICAART-23.
- Our paper “Safe Policy Improvement for POMDPs via Finite-State Controllers” has been accepted at AAAI-23.
- Two talks at the AAAI 2022 Fall Symposium.
- I am serving as a PC member for AISTATS 2023.
- Our paper “Robust Anytime Learning of Markov Decision Processes” has been accepted at NeurIPS-22.
- I am serving as a PC member for ICAPS 2023.
- I am serving as a PC member for NeurIPS 2022.
- Our paper “Safety-constrained reinforcement learning with a distributional safety critic” has been published at Machine Learning.
- Two papers presented at the ALA 2022 workshop on Safe Transfer in RL and Solving Hidden Parameter MDPs with Hindsight.
- Invited talk for the Oden Institute seminar at UT Austin.
- Talk at the LiVe-22 workshop about Safe Transfer in Reinforcement Learning.
- Talk at the ADML meetup about Ensuring Safety for Reinforcement Learning.
- I am serving as a PC member for ICML 2022.
- Talk at the iVerif workshop on Safety Abstractions.
- I am serving as a PC member for the Planning and Learning track at ICAPS 2022.
- Talk at the PRL workshop.
- At ICAPS-21 attending the mentoring program.
- Invited talk at the Center for Artificial Intelligence.
- At AAMAS-21 presenting the AlwaysSafe paper.
- Talk at the LiVe-21 workshop about AlwaysSafe.
- Guest lecture on Safe RL at the Algorithms for Intelligent Decision Making course.
- Invited talk at the SWS-seminar about our AAMAS paper.
- Our paper “AlwaysSafe: Reinforcement Learning Without Safety Constraint Violations During Training” has been accepted at AAMAS-21.
- Our paper “WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning” has been accepted at AAAI-21.
- I am serving as a PC member for AAAI-21.
- At AAMAS-20 presenting the paper “Safe Policy Improvement with an Estimated Baseline Policy.”
- Released gym-factored, a collection of factored environments that are OpenAI Gym compliant.
- At IJCAI-19 presenting our paper on structure learning for safe RL.
- At IJCAI-19 participating on the doctoral consortium .
- Attending the conference RLDM-19.
- Starting my interniship at MSR Montreal with Romain Laroche and Remi Tachet des Combes.
- I got the prize for Best Poster in our department’s poster session.
- In Hilversum, presenting our work on reinforcement learning at the ICT.Open-19.
- At AAAI-19 presenting our paper on safe policy improvement in factored environments.
- I am co-organizing the Belgium Netherlands Workshop on Reinforcement Learning (BeNeRL-18).
- I am attending the 14th European Workshop on Reinforcement Learning (EWRL-18).
- I gave a contributed talk at the ICML-18 Workshop on Planning and Learning.
- I presented a poster at ICAPS-18.
- I am helping the local organizing committee of the ICAPS-18 at Delft.
- Attending the ICAPS-18 summer school at Noordwijk.
- I presented a poster at the Energy Event promoted by the PowerWeb Institute.
- Presenting a poster at the EEMCS’s PhD Event.
- I attended the ACAI Summer School on Reinforcement Learning.
- I attended the 19th European Agent Systems Summer School.