Sign in
Sample-Efficient Goal-Conditioned Reinforcement Learning via Predictive Information Bottleneck for Goal Representation Learning.
Qiming Zou
Einoshin Suzuki
Published in:
ICRA (2023)
Keyphrases
</>
reinforcement learning
information bottleneck
learning algorithm
learning process
active learning
supervised learning
sample size
information theoretic
learning problems
machine learning
xml documents
prior knowledge
domain knowledge
maximum entropy