Login / Signup
Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning.
Christopher Hoang
Sungryull Sohn
Jongwook Choi
Wilka Carvalho
Honglak Lee
Published in:
CoRR (2021)
Keyphrases
</>
reinforcement learning
function approximation
feature vectors
image features
state space
geometrical features
temporal difference
machine learning
markov decision processes
optimal policy
neural network
feature set
path planning
hidden markov models
object recognition
computer vision
elastic image registration