HHAL (Le Centre pour la Communication Scientifique Directe)21h ago

Learning Feasible Scalarizations in Constrained Markov Decision Processes Using a Stochastic Meta-Policy

Ozaibi, Youssef, Al·Amar Ramdane-Cherif·Maxime Toquebiau·Manolo Dulva Hina

International audience

Read at HAL (Le Centre pour la Communication Scientifique Directe)

Tags

Reinforcement Learning in RoboticsArtificial Intelligence