PolyTask: Learning Unified Policies through Behavior Distillation.

Siddhant Haldar Lerrel Pinto

Published in: CoRR (2023)

Keyphrases

prior knowledge
learning process
active learning
online learning
data sets
learning algorithm
information systems
reinforcement learning
knowledge acquisition
learning community
inductive inference
e learning
case study
probabilistic model
learning scheme
learning mechanism