A breakthrough post-training result for physical AI via self-play: a strong base model like S1 can learn to complete extremely dexterous and dynamic tasks, like soccer, by competing against itself in a simulation.
Read in full here:
A breakthrough post-training result for physical AI via self-play: a strong base model like S1 can learn to complete extremely dexterous and dynamic tasks, like soccer, by competing against itself in a simulation.
Read in full here: