Task-Guided Inverse Reinforcement Learning under Partial Information.

Franck Djeumou Murat Cubuktepe Craig Lennon Ufuk Topcu

Published in: ICAPS (2022)

Keyphrases

partial information
inverse reinforcement learning
bayesian nonparametric
partially observable environments
incomplete information
preference elicitation
reward function
reinforcement learning
resource allocation
autonomous agents