https://openreview.net/forum?id=yqLFb0RnDW&referrer=%5Bthe%20profile%20of%20Zi-ang%20Cao%5D(%2Fprofile%3Fid%3D~Zi-ang_Cao1)
Robot behavior policies trained via imitation learning are prone to failure under conditions that deviate from their training data. Thus, algorithms that...
failure modesruntime monitoringunpackinggenerativepolicies
https://openreview.net/forum?id=j1B3Id9CLm&referrer=%5Bthe%20profile%20of%20Zi-ang%20Cao%5D(%2Fprofile%3Fid%3D~Zi-ang_Cao1)
Robot behavior policies trained via imitation learning are prone to failure under conditions that deviate from their training data. Thus, algorithms that...
failure modesruntime monitoringunpackinggenerativepolicies