Preference Models
Preference Model is building reinforcement learning environments.
South Park CommonsSeedGeneral Software
What they do
Problem
Developers and researchers need robust environments to train and evaluate reinforcement learning systems.
Solution
It provides reinforcement learning environments for building, training, and testing RL agents.
Who it's for
Reinforcement learning researchers and developers building RL agents.
Founders
Jennifer Zhou
Ex-Stripe. Ex-Anthropic. Currently doing a startup.
Open roles 3
Company timeline
- StatusSeed
- LocationSan Francisco
