4 papers
Learning visual policies for building 3D shape categories
Alexander Pashevich, Igor Kalevatykh, Ivan Laptev +1
Manipulation and assembly tasks require non-trivial planning of actions depending on the environment and the final goal. Previous work in this domain often assembles particular ins…
Learning to combine primitive skills: A step towards versatile robotic manipulation
Robin Strudel, Alexander Pashevich, Igor Kalevatykh +3
Manipulation tasks such as preparing a meal or assembling furniture remain highly challenging for robotics and vision. Traditional task and motion planning (TAMP) methods can solve…
Learning to Augment Synthetic Images for Sim2Real Policy Transfer
Alexander Pashevich, Robin Strudel, Igor Kalevatykh +2
Vision and learning have made significant progress that could improve robotics policies for complex tasks and environments. Learning deep neural networks for image understanding, h…
Modulated Policy Hierarchies
Alexander Pashevich, Danijar Hafner, James Davidson +2
Solving tasks with sparse rewards is a main challenge in reinforcement learning. While hierarchical controllers are an intuitive approach to this problem, current methods often req…