Learning Human Objectives from Sequences of Physical Corrections.

Mengxi Li Alper Canberk Dylan P. Losey Dorsa Sadigh

Published in: CoRR (2021)

Keyphrases

learning algorithm
real world
learning process
prior knowledge
reinforcement learning
online learning
learning systems
data sets
human experts
human interaction
database
incremental learning
learning scenarios
supervised learning
probabilistic model
active learning
objective function