Inventor

Levine Sergey

US20 patents

⚠️ This page may combine multiple inventors who share the name “Levine Sergey”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

Levine Sergey

GOOGLE LLC

Deep reinforcement learning for robotic manipulation

Deep machine learning methods and apparatus for robotic grasping

Deep machine learning methods and apparatus for robotic grasping

Deep machine learning methods and apparatus for robotic grasping

Data-efficient hierarchical reinforcement learning

System and methods for training robot policies in the real world

Machine learning methods and apparatus for semantic robotic grasping

Deep machine learning methods and apparatus for robotic grasping

System(s) and method(s) of using imitation learning in training and refining robotic control policies

Deep reinforcement learning for robotic manipulation

Viewpoint invariant visual servoing of robot end effector using recurrent neural network

Data-efficient hierarchical reinforcement learning

System(s) and method(s) of using imitation learning in training and refining robotic control policies

Deep reinforcement learning for robotic manipulation

Mitigating reality gap through training a simulation-to-real model using a vision-based robot task model

Efficient adaption of robot control policy for new task using meta-learning based on meta-imitation learning and meta-reinforcement learning

GOOGLE INC

Deep machine learning methods and apparatus for robotic grasping

Deep machine learning methods and apparatus for robotic grasping

Machine learning methods and apparatus related to predicting motion(s) of object(s) in a robot&#39;s environment based on image(s) capturing the object(s) and based on parameter(s) for future robot movement in the environment

TOYOTA RES INST INC

Planning-aware prediction for control-aware autonomous driving modules

Machine learning methods and apparatus related to predicting motion(s) of object(s) in a robot's environment based on image(s) capturing the object(s) and based on parameter(s) for future robot movement in the environment