Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:person
|
| gptkbp:advisorTo |
gptkb:Pieter_Abbeel
|
| gptkbp:education |
gptkb:UC_Berkeley
|
| gptkbp:employer |
gptkb:OpenAI
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning deep learning |
| gptkbp:founder |
gptkb:OpenAI
|
| https://www.w3.org/2000/01/rdf-schema#label |
John Schulman
|
| gptkbp:knownFor |
gptkb:Proximal_Policy_Optimization_(PPO)
gptkb:Trust_Region_Policy_Optimization_(TRPO) co-founder of OpenAI work on reinforcement learning |
| gptkbp:nationality |
gptkb:American
|
| gptkbp:notableWork |
work on robotics
PPO algorithm TRPO algorithm |
| gptkbp:occupation |
gptkb:computer_scientist
|
| gptkbp:publishedIn |
gptkb:arXiv
gptkb:ICLR gptkb:NeurIPS |
| gptkbp:bfsParent |
gptkb:OpenAI
|
| gptkbp:bfsLayer |
5
|