WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning Q Yang, TD Simão, SH Tindemans, MTJ Spaan AAAI, 10639-10646, 2021 | 114 | 2021 |
AlwaysSafe: Reinforcement learning without safety constraint violations during training TD Simão, N Jansen, MTJ Spaan AAMAS, 1226-1235, 2021 | 48 | 2021 |
Safety-constrained reinforcement learning with a distributional safety critic Q Yang, TD Simão, SH Tindemans, MTJ Spaan Machine Learning 112 (3), 859-887, 2023 | 36 | 2023 |
Safe Policy Improvement with an Estimated Baseline Policy TD Simão, R Laroche, R Tachet des Combes AAMAS, 1269-1277, 2020 | 33* | 2020 |
Safe Policy Improvement with Baseline Bootstrapping in Factored Environments TD Simão, MTJ Spaan AAAI, 4967-4974, 2019 | 32 | 2019 |
Robust anytime learning of Markov decision processes M Suilen, TD Simão, D Parker, N Jansen NeurIPS, 28790-28802, 2022 | 24 | 2022 |
Decision-making under uncertainty: beyond probabilities: Challenges and perspectives T Badings, TD Simão, M Suilen, N Jansen International Journal on Software Tools for Technology Transfer 25 (3), 375-391, 2023 | 12 | 2023 |
Safe policy improvement for POMDPs via finite-state controllers TD Simão, M Suilen, N Jansen AAAI, 15109-15117, 2023 | 12 | 2023 |
Structure Learning for Safe Policy Improvement TD Simão, MTJ Spaan IJCAI, 3453-3459, 2019 | 11 | 2019 |
Reinforcement Learning by Guided Safe Exploration Q Yang, TD Simão, N Jansen, SH Tindemans, MTJ Spaan ECAI, 2858-2865, 2023 | 9* | 2023 |
Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation Y Hogewind, TD Simão, T Kachman, N Jansen ICLR, 2023 | 9 | 2023 |
A Modern Perspective on Safe Automated Driving for Different Traffic Dynamics Using Constrained Reinforcement Learning D Kamran, TD Simão, Q Yang, CT Ponnambalam, J Fischer, MTJ Spaan, ... 2022 IEEE 25th International Conference on Intelligent Transportation …, 2022 | 9 | 2022 |
Scalable Safe Policy Improvement via Monte Carlo Tree Search A Castellini, F Bianchi, E Zorzi, TD Simão, A Farinelli, MTJ Spaan ICML, 3732-3756, 2023 | 5 | 2023 |
More for Less: Safe Policy Improvement With Stronger Performance Guarantees P Wienhöft, M Suilen, TD Simão, C Dubslaff, C Baier, N Jansen IJCAI, 4406-4415, 2023 | 5 | 2023 |
Act-then-measure: reinforcement learning for partially observable environments with active measuring M Krale, TD Simão, N Jansen ICAPS, 212-220, 2023 | 5 | 2023 |
Recursive small-step multi-agent A* for dec-POMDPs W Koops, N Jansen, S Junges, TD Simão IJCAI, 5402-5410, 2023 | 2 | 2023 |
Planejamento probabilístico com becos sem saída TD Simão Universidade de São Paulo, 2017 | 2 | 2017 |
Utilização de algoritmos genéticos para otimização de soluções para o timetabling escolar TD SIMÃO Tese apresentada ao Departamento de Ciência da Computação da Universidade …, 2013 | 2 | 2013 |
Risk-aware curriculum generation for heavy-tailed task distributions C Koprulu, TD Simão, N Jansen, U Topcu UAI, 1132-1142, 2023 | 1 | 2023 |
Safe and Sample-Efficient Reinforcement Learning Algorithms for Factored Environments. TD Simão IJCAI, 6460-6461, 2019 | 1 | 2019 |