Learning concepts with energy functions
Energy-based model learns spatial concepts (near, above, between) from five demonstrations with cross-domain transfer from 2D to 3D robotics.
Excerpt
We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, and furthest, expressed as sets of 2d points. Our model learns these concepts after only five demonstrations. We also show cross-domain transfer: we use concepts learned in a 2d particle environment to solve tasks on a 3-dimensional physics-based robot.
Read at source: https://openai.com/index/learning-concepts-with-energy-functions