Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning.

Valerie Chen Abhinav Gupta Kenneth Marino

Published in: CoRR (2020)

Keyphrases

reinforcement learning
human behavior
human subjects
machine learning
human users
human experts
learning algorithm
artificial intelligence
markov decision processes
virtual agents
computer vision
supervised learning
function approximation
human beings
computer programs