Login / Signup
On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning.
Mandi Zhao
Pieter Abbeel
Stephen James
Published in:
NeurIPS (2022)
Keyphrases
</>
fine tuning
reinforcement learning
viable alternative
fine tune
fine tuned
state space
dynamic programming
function approximation
multi agent
decision making
information retrieval
neural network
database
similarity measure
image sequences
action selection
learning capabilities
data sets