Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:software
|
| gptkbp:application |
gptkb:machine_learning
gptkb:reinforcement_learning decision making |
| gptkbp:developedBy |
gptkb:Meta_AI
|
| gptkbp:documentation |
https://facebookresearch.github.io/ReAgent/
|
| gptkbp:formerName |
gptkb:Horizon
|
| https://www.w3.org/2000/01/rdf-schema#label |
ReAgent
|
| gptkbp:license |
gptkb:MIT_License
|
| gptkbp:openSource |
true
|
| gptkbp:platform |
gptkb:Windows
gptkb:macOS gptkb:Linux |
| gptkbp:programmingLanguage |
gptkb:Python
|
| gptkbp:repository |
https://github.com/facebookresearch/ReAgent
|
| gptkbp:supports |
batch RL
counterfactual policy evaluation online RL |
| gptkbp:usedFor |
optimization
recommendation systems personalization |
| gptkbp:bfsParent |
gptkb:Meta_AI
|
| gptkbp:bfsLayer |
5
|