Statements (13)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:project
|
| gptkbp:aims_to |
improve AI training methods
|
| gptkbp:applies_to |
gptkb:robot
natural language processing game playing |
| gptkbp:developed_by |
gptkb:Open_AI
|
| gptkbp:focuses_on |
reinforcement learning
|
| gptkbp:has_programs |
gptkb:engine
healthcare |
| https://www.w3.org/2000/01/rdf-schema#label |
Project REINFORCE
|
| gptkbp:utilizes |
policy gradient methods
|
| gptkbp:bfsParent |
gptkb:Spartan-III_program
|
| gptkbp:bfsLayer |
5
|