We provide real-world data, policy evaluation, and physical environments for reinforcement learning, helping teams train, test, and improve robot models
We provide real-world data, policy evaluation, and physical environments for reinforcement learning, helping teams train, test, and improve robot models. Follow a checkpoint 4inputs, defined once 1Policy Upload a model checkpoint or connect an inference endpoint. Specify the task, test environment, and success criteria. SE3 uses the same evaluation protocol across test stations and policy versions