Learning from Unreliable Human Action Advice in Interactive Reinforcement Learning.

Lisa Scherf Cigdem Turan Dorothea Koert

Published in: Humanoids (2022)

Keyphrases

reinforcement learning
learning process
learning algorithm
human actions
spatio temporal
active learning
action recognition
three dimensional
prior knowledge
machine learning
video sequences
low level
supervised learning
markov decision processes
human activities