Thiago D. Simão

Safe Policy Improvement with Baseline Bootstrapping in Factored Environments

Matthijs T. J. Spaan, Thiago D. Simão, M. Spaan, 2019, AAAI.

Safe and Sample-Efficient Reinforcement Learning Algorithms for Factored Environments

Thiago D. Simão, 2019, IJCAI.

Structure Learning for Safe Policy Improvement

Matthijs T. J. Spaan, Thiago D. Simão, M. Spaan, 2019, IJCAI.

Safe Policy Improvement with an Estimated Baseline Policy

Romain Laroche, Thiago D. Simão, Rémi Tachet des Combes, 2019, AAMAS.

When a Robot Reaches Out for Human Help

Denis Deratani Mauá, Thiago D. Simão, Leliane Nunes de Barros, 2018, IBERAMIA.

AlwaysSafe: Reinforcement Learning without Safety Constraint Violations during Training

Nils Jansen, Thiago D. Simão, M. Spaan, 2021, AAMAS.

WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning

Matthijs T. J. Spaan, Simon H. Tindemans, Thiago D. Simão, 2021, AAAI.

Safe Policy Improvement with an Estimated Baseline Policy

Romain Laroche, Thiago D. Simão, Rémi Tachet des Combes, 2020, AAMAS.