Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
reinforcement learning algorithm
|
| gptkbp:approach |
hierarchical reinforcement learning
|
| gptkbp:author |
gptkb:Ilya_Sutskever
gptkb:Peter_Abbeel gptkb:John_Schulman gptkb:Xi_Chen gptkb:Yan_Duan |
| gptkbp:citation |
gptkb:Meta-Learning_Shared_Hierarchies
gptkb:arXiv_preprint_arXiv:1710.09767 |
| gptkbp:field |
gptkb:machine_learning
gptkb:reinforcement_learning meta-learning |
| gptkbp:fullName |
gptkb:Meta_Learning_Shared_Hierarchies
|
| https://www.w3.org/2000/01/rdf-schema#label |
MLSH
|
| gptkbp:introduced |
gptkb:OpenAI
gptkb:Meta-Learning_Shared_Hierarchies |
| gptkbp:publicationYear |
2017
|
| gptkbp:purpose |
improve sample efficiency in RL
learn reusable sub-policies |
| gptkbp:url |
https://arxiv.org/abs/1710.09767
|
| gptkbp:uses |
policy gradient methods
|
| gptkbp:bfsParent |
gptkb:Miaoli_Senior_High_School
|
| gptkbp:bfsLayer |
6
|