Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces.

Takahisa Imagawa Takuya Hiraoka Yoshimasa Tsuruoka

Published in: CoRR (2021)

Keyphrases

reinforcement learning
feature vectors
nearest neighbor searching
optimal policy
neural network
function approximation
markov decision processes
image features
feature set
state space
learning algorithm
vector space
meta level
machine learning
data hiding
model free
data sets