5 papers
Visionary: Vision architecture discovery for robot learning
Iretiayo Akinola, Anelia Angelova, Yao Lu +5
We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visua…
Meta-Learning via Learned Loss
Sarah Bechtle, Artem Molchanov, Yevgen Chebotar +4
Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper…
Learning Latent Space Dynamics for Tactile Servoing
Giovanni Sutanto, Nathan Ratliff, Balakumar Sundaralingam +4
To achieve a dexterous robotic manipulation, we need to endow our robot with tactile feedback capability, i.e. the ability to drive action based on tactile sensing. In this paper,…
Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience
Yevgen Chebotar, Ankur Handa, Viktor Makoviychuk +4
We consider the problem of transferring policies to the real world by training on a distribution of simulated scenarios. Rather than manually tuning the randomization of simulation…
Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets
Karol Hausman, Yevgen Chebotar, Stefan Schaal +2
Imitation learning has traditionally been applied to learn a single task from demonstrations thereof. The requirement of structured and isolated demonstrations limits the scalabili…