
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat th...
read it

Deep Double Descent: Where Bigger Models and More Data Hurt
We show that a variety of modern deep learning tasks exhibit a "doubled...
read it

Generating Long Sequences with Sparse Transformers
Transformers are powerful sequence models, but require time and memory t...
read it

FFJORD: Freeform Continuous Dynamics for Scalable Reversible Generative Models
A promising class of generative models maps points from a simple distrib...
read it

Addressing the Rare Word Problem in Neural Machine Translation
Neural Machine Translation (NMT) is a new approach to machine translatio...
read it

Exploiting Similarities among Languages for Machine Translation
Dictionaries and phrase tables are the basis of modern statistical machi...
read it

Sequence to Sequence Learning with Neural Networks
Deep Neural Networks (DNNs) are powerful models that have achieved excel...
read it

Reinforcement Learning Neural Turing Machines  Revised
The Neural Turing Machine (NTM) is more expressive than all previously c...
read it

Distributed Representations of Words and Phrases and their Compositionality
The recently introduced continuous Skipgram model is an efficient metho...
read it

Learning Factored Representations in a Deep Mixture of Experts
Mixtures of Experts combine the outputs of several "expert" networks, ea...
read it

MuProp: Unbiased Backpropagation for Stochastic Neural Networks
Deep neural networks are powerful parametric models that can be trained ...
read it

ThirdPerson Imitation Learning
Reinforcement learning (RL) makes it possible to train agents capable of...
read it

Towards Principled Unsupervised Learning
General unsupervised learning is a longstanding conceptual problem in m...
read it

TensorFlow: LargeScale Machine Learning on Heterogeneous Distributed Systems
TensorFlow is an interface for expressing machine learning algorithms, a...
read it

Emergent Complexity via MultiAgent Competition
Reinforcement learning algorithms can train agents that solve problems i...
read it

Continuous Adaptation via MetaLearning in Nonstationary and Competitive Environments
Ability to continuously learn and adapt from limited experience in nonst...
read it

OneShot Imitation Learning
Imitation learning has been commonly applied to solve different tasks in...
read it

Neural GPUs Learn Algorithms
Learning an algorithm from examples is a fundamental problem that has be...
read it

Neural RandomAccess Machines
In this paper, we propose and investigate a new neural network architect...
read it

Move Evaluation in Go Using Deep Convolutional Neural Networks
The game of Go is more challenging than other board games, due to the di...
read it

Recurrent Neural Network Regularization
We present a simple regularization technique for Recurrent Neural Networ...
read it

Extensions and Limitations of the Neural GPU
The Neural GPU is a recent model that can learn algorithms such as multi...
read it

Evolution Strategies as a Scalable Alternative to Reinforcement Learning
We explore the use of Evolution Strategies (ES), a class of black box op...
read it

Continuous Deep QLearning with Modelbased Acceleration
Modelfree reinforcement learning has been successfully applied to a ran...
read it

RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning
Deep reinforcement learning (deep RL) has been successful in learning so...
read it

Variational Lossy Autoencoder
Representation learning seeks to expose certain aspects of observed data...
read it

Improving Variational Inference with Inverse Autoregressive Flow
The framework of normalizing flows provides a general strategy for flexi...
read it

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
This paper describes InfoGAN, an informationtheoretic extension to the ...
read it

Learning to Execute
Recurrent Neural Networks (RNNs) with Long ShortTerm Memory units (LSTM...
read it

Adding Gradient Noise Improves Learning for Very Deep Networks
Deep feedforward and recurrent networks have achieved impressive results...
read it

Estimating the Hessian by Backpropagating Curvature
In this work we develop Curvature Propagation (CP), a general technique ...
read it

Intriguing properties of neural networks
Deep neural networks are highly expressive models that have recently ach...
read it

Improving neural networks by preventing coadaptation of feature detectors
When a large feedforward neural network is trained on a small training s...
read it

An online sequencetosequence model for noisy speech recognition
Generative models have long been the dominant approach for speech recogn...
read it

Learning to Generate Reviews and Discovering Sentiment
We explore the properties of bytelevel recurrent language models. When ...
read it

Learning Online Alignments with Continuous Rewards Policy Gradient
Sequencetosequence models with soft attention had significant success ...
read it

Multitask Sequence to Sequence Learning
Sequence to sequence learning has recently emerged as a new paradigm in ...
read it

A Neural Transducer
Sequencetosequence models have achieved impressive results on various ...
read it

Neural Programmer: Inducing Latent Programs with Gradient Descent
Deep neural networks have achieved impressive supervised classification ...
read it

Grammar as a Foreign Language
Syntactic constituency parsing is a fundamental problem in natural langu...
read it

Some Considerations on Learning to Explore via MetaReinforcement Learning
We consider the problem of exploration in meta reinforcement learning. T...
read it

GamePad: A Learning Environment for Theorem Proving
In this paper, we introduce a system called GamePad that can be used to ...
read it
Ilya Sutskever
is this you? claim profile
Ilya Sutskever is an informatics scientist who works in the field of machine learning and currently serves as OpenAI’s Chief Scientist. He is the coinventor of the renowned neural network AlexNet. He and Oriol Vinyals and Quoc Le invented Sequence to Sequence Learning. Sutskever is also AlphaGo and TensorFlow coinventor.
Sutskever obtained his B.Sc, M.Sc, and Ph.D. in computer science from the Department of Computer Science at the University of Toronto, under Geoffrey Hinton’s supervision.
After graduating in 2012, Sutskever spent two months at Stanford University as a postdoc with Andrew Ng. He then returned to the University of Toronto and joined the new Hinton research group DNNResearch. Google acquired DNNResearch four months later, in March 2013 and employed Sutskever as a Google Brain research scientist. At Google Brain, Sutskever worked with Oriol Vinyals and Quoc Le on sequence by sequence learning algorithms.
In 2015, Sutskever had been nominated for the MIT Technology Review 35 Innovators Under 35. At the end of 2015, Sutskever left Google to be the Director of the newly founded OpenAI Institute.