Current frame
Reinforcement learning engineer and OLMo 3 coauthor.
Atlas / People / Detail
Huang, Costa
Costa Huang is a reinforcement learning researcher and the creator of CleanRL; his public GitHub profile lists Periodic Labs as his current affiliation and AllenAI and Hugging Face as previous affiliations.
Profile status: updated
Extended note
His homepage notes that he passed his PhD defense at Drexel University in 2023.