RL-CycleGAN: Reinforcement Learning Aware Simulation-to-Real

Kanishka Rao, C.J. Harris, Alex Irpan, +3

Artificial IntelligenceMachine VisionMachine LearningEngineeringDeep Reinforcement Learning +12

BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning

Eric Jang, Alex Irpan, Mohi Khansari, +5

arXiv (Cornell University)

Artificial IntelligenceFew-shot LearningEngineeringMachine LearningIntelligent Robotics +14

RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer

Daniel E. Ho, Kanishka Rao, Zhuo Xu, +3

Artificial IntelligenceEngineeringMachine LearningDoor OpeningObject-aware Approach +14

Data-Efficient Learning for Sim-to-Real Robotic Grasping using Deep Point Cloud Prediction Networks

Xinchen Yan, Mohi Khansari, Jasmine Hsu, +4

arXiv (Cornell University)

Artificial IntelligenceGeometric LearningEngineeringMachine LearningDexterous Manipulation +17

Learning Latent Plans from Play

Corey Lynch, Mohi Khansari, Ted Xiao, +4

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningSequential LearningGame Theory +14

Watch, Try, Learn: Meta-Learning from Demonstrations and Reward

Allan Zhou, Eric Jang, Daniel Kappler, +7

arXiv (Cornell University)

Artificial IntelligenceSparse Reward FeedbackEngineeringMachine LearningCognition +14

Learning Contracting Vector Fields For Stable Imitation Learning

Vikas Sindhwani, Stephen Tu, Mohi Khansari

arXiv (Cornell University)

Artificial IntelligenceGeometric LearningEngineeringMachine LearningLearning Control +14

RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real

Kanishka Rao, C.J. Harris, Alex Irpan, +3

arXiv (Cornell University)

Online Object Representations with Contrastive Learning

Sören Pirk, Mohi Khansari, Yunfei Bai, +2

arXiv (Cornell University)

EngineeringMachine LearningObject CategorizationSelf-supervised ApproachMonocular Videos +15

Modeling Long-horizon Tasks as Sequential Interaction Landscapes

Sören Pirk, Karol Hausman, Alexander Toshev, +1

arXiv (Cornell University)

Artificial IntelligenceEngineeringMachine LearningDeep Learning NetworkCognitive Robotics +14