no code implementations • 11 May 2019 • Angelina Wang, Thanard Kurutach, Kara Liu, Pieter Abbeel, Aviv Tamar
We further demonstrate our approach on learning to imagine and execute in 3 environments, the final of which is deformable rope manipulation on a PR2 robot.
1 code implementation • ICML 2020 • Kara Liu, Thanard Kurutach, Christine Tung, Pieter Abbeel, Aviv Tamar
In visual planning (VP), an agent learns to plan goal-directed behavior from observations of a dynamical system obtained offline, e. g., images obtained from self-supervised robot interaction.