Task-Guided Inverse Reinforcement Learning Under Partial Information.

Franck Djeumou Murat Cubuktepe Craig Lennon Ufuk Topcu

Published in: CoRR (2021)

Keyphrases

partial information
inverse reinforcement learning
bayesian nonparametric
incomplete information
partially observable environments
preference elicitation
reward function
multi agent systems
objective function
expert systems
hidden markov models
autonomous agents