Inventor

KAVUKCUOGLU KORAY

GB37 patents

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

KAVUKCUOGLU KORAY

DEEPMIND TECH LTD

Distributed training of reinforcement learning systems

Reinforcement learning using target neural networks

Image processing with recurrent attention

Spatial transformer modules

Spatial transformer modules

Asynchronous deep reinforcement learning

Action selection for reinforcement learning using neural networks

Generating discrete latent representations of input data items

Image processing with recurrent attention

Image processing with recurrent attention

Using hierarchical representations for neural network architecture searching

Spatial transformer modules

Reinforcement learning with auxiliary tasks

Asynchronous deep reinforcement learning

Asynchronous deep reinforcement learning

Distributed training using actor-critic reinforcement learning with off-policy correction factors

Environment navigation using reinforcement learning

Environment navigation using reinforcement learning

Generating predictions characterizing images using glimpses extracted from the images

Image processing of an environment to select an action to be performed by an agent interacting with the environment

Reinforcement learning with auxiliary tasks

Reinforcement learning using baseline and policy neural networks

Training neural networks using synthetic gradients

Whitened neural network layers

Progressive neural networks

Distributed training using actor-critic reinforcement learning with off-policy correction factors

Distributed training using actor-critic reinforcement learning with off-policy correction factors

Progressive neural networks

Asynchronous deep reinforcement learning

Progressive neural networks

Action selection for reinforcement learning using a manager neural network that generates goal vectors defining agent objectives

Distributed training of reinforcement learning systems

Training machine learning models using task selection policies to increase learning progress

NEC LAB AMERICA INC

Two-stage multiple kernel learning method

Latent factor dependency structure determination

GOOGLE INC

Methods and apparatus for reinforcement learning

MELVIN IAIN

Distributed artificial intelligence services on a cell phone