Home
EPiC Series
Kalpa Publications
Preprints
For Authors
For Editors
Author
:
Shibani
Publications
Learning to Self-Modify Rewards with Bi-Level Gradients
Aiden Boyd
,
Shibani
and
Will Callaghan
EasyChair Preprint 8260
Learning to Self-Modify Rewards with Implicit Gradients
Aiden Boyd
,
Shibani
and
Will Callaghan
EasyChair Preprint 8260
Keyphrases
meta-learning
,
Reinforcement Learning
,
Reward Shaping
.
Copyright © 2012-2024 easychair.org. All rights reserved.
