Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring

von Krale, Merlijn
Veröffentlicht in International Conference on Automated Planning and Scheduling (33. : 2023 : Prag) Thirty-third International Conference on Automated Planning and Scheduling (ICAPS 2023) (2023)

SAFE POLICY IMPROVEMENT WITH AN ESTIMATED BASELINE POLICY

von Simáo, Thiago D.
Veröffentlicht in AAMAS (19. : 2020 : Online) International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2020) ; Volume 2 of 3 (2021)

Robust Anytime Learning of Markov Decision Processes

von Suilen, Marnix
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 37 of 50 (2023)

ALWAYSSAFE: REINFORCEMENT LEARNING WITHOUT SAFETY CONSTRAINT VIOLATIONS DURING TRAINING

von Simão, Thiago D.
Veröffentlicht in AAMAS (20. : 2021 : Online) 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021) ; Volume 2 of 3 (2021)