Search Results for author: Kaushik Shivakumar

Found 5 papers, 0 papers with code

DEFT: Diverse Ensembles for Fast Transfer in Reinforcement Learning

no code implementations26 Sep 2022 Simeon Adebola, Satvik Sharma, Kaushik Shivakumar

In this work, we present Diverse Ensembles for Fast Transfer in RL (DEFT), a new ensemble-based method for reinforcement learning in highly multimodal environments and improved transfer to unseen environments.

Ensemble Learning reinforcement-learning +1

Learning to Fold Real Garments with One Arm: A Case Study in Cloud-Based Robotics Research

no code implementations21 Apr 2022 Ryan Hoque, Kaushik Shivakumar, Shrey Aeron, Gabriel Deza, Aditya Ganapathi, Adrian Wong, Johnny Lee, Andy Zeng, Vincent Vanhoucke, Ken Goldberg

Autonomous fabric manipulation is a longstanding challenge in robotics, but evaluating progress is difficult due to the cost and diversity of robot hardware.

Imitation Learning

CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss

no code implementations27 Nov 2018 Blaine Rister, Darvin Yi, Kaushik Shivakumar, Tomomi Nobashi, Daniel L. Rubin

To achieve the best results from data augmentation, our model uses the intersection-over-union (IOU) loss function, a close relative of the Dice loss.

Data Augmentation Image Segmentation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.