I
Ilya Sutskever
Researcher at OpenAI
Publications - 137
Citations - 294374
Ilya Sutskever is an academic researcher from OpenAI. The author has contributed to research in topics: Artificial neural network & Reinforcement learning. The author has an hindex of 75, co-authored 131 publications receiving 235539 citations. Previous affiliations of Ilya Sutskever include Google & University of Toronto.
Papers
More filters
Proceedings Article
Neural GPUs Learn Algorithms
ukasz Kaiser,Ilya Sutskever +1 more
TL;DR: It is shown that the Neural GPU can be trained on short instances of an algorithmic task and successfully generalize to long instances, and a technique for training deep recurrent networks: parameter sharing relaxation is introduced.
Posted Content
Third-Person Imitation Learning
TL;DR: In this article, the authors present a method for unsupervised third-person imitation learning, where the agent is provided with a sequence of states and a specification of the actions that it should have taken.
Posted Content
Generative Language Modeling for Automated Theorem Proving.
Stanislas Polu,Ilya Sutskever +1 more
TL;DR: This work presents an automated prover and proof assistant, GPT-f, for the Metamath formalization language, and analyzes its performance, finding new short proofs that were accepted into the mainMetamath library, which is to this knowledge, the first time a deep-learning based system has contributed proofs that are adopted by a formal mathematics community.
Posted Content
Move Evaluation in Go Using Deep Convolutional Neural Networks
TL;DR: A large 12-layer convolutional neural network is trained by supervised learning from a database of human professional games that beats the traditional search program GnuGo in 97% of games, and matched the performance of a state-of-the-art Monte-Carlo tree search that simulates a million positions per move.
Proceedings Article
MuProp: Unbiased Backpropagation for Stochastic Neural Networks
TL;DR: MuProp is presented, an unbiased gradient estimator for stochastic networks, designed to make this task easier by improving on the likelihood-ratio estimator by reducing its variance using a control variate based on the first-order Taylor expansion of a mean-field network.