Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning.

Tu Trinh Daniel S. Brown

Published in: CoRR (2022)

Keyphrases

inverse reinforcement learning
bayesian nonparametric
partially observable environments
preference elicitation
bayesian networks
reward function
gaussian process
decision theory
variational inference
maximum likelihood
mixture model
bayesian inference
posterior distribution
gaussian processes
simple examples