Sign in
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning.
Mitsuhiko Nakamoto
Yuexiang Zhai
Anikait Singh
Max Sobol Mark
Yi Ma
Chelsea Finn
Aviral Kumar
Sergey Levine
Published in:
CoRR (2023)
Keyphrases
</>
fine tuning
online learning
real time
reinforcement learning
fine tuned
viable alternative
batch mode
machine learning
online training
fine tune
general purpose
multi agent
function approximation
training process
multi view
domain specific
active learning
learning environment