⚡ LIVE

Search AI News

Find articles from 100+ AI sources

🔍

Found 1,882 results for "OpenAI"

1,882 articles
OpenAI News Models Dec 6, 2017 👁 17

Block-sparse GPU kernels

We’re releasing highly-optimized GPU kernels for an underexplored class of neural network architectures:…

OpenAI News Models Dec 4, 2017 👁 20

Learning sparse neural networks through L₀ regularization

Learning sparse neural networks through L₀ regularization. OpenAI News - artificial intelligence news.

OpenAI News Models Nov 2, 2017 👁 17

Interpretable and pedagogical examples

Interpretable and pedagogical examples. OpenAI News - artificial intelligence news.

OpenAI News Models Oct 26, 2017 👁 16

Learning a hierarchy

We’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for…

OpenAI News Models Oct 19, 2017 👁 21

Generalizing from simulation

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on…

OpenAI News Models Oct 18, 2017 👁 18

Asymmetric actor critic for image-based robot learning

Asymmetric actor critic for image-based robot learning. OpenAI News - artificial intelligence news.

OpenAI News Models Oct 18, 2017 👁 21

Sim-to-real transfer of robotic control with dynamics randomization

Sim-to-real transfer of robotic control with dynamics randomization. OpenAI News - artificial intelligence…

OpenAI News Models Oct 17, 2017 👁 25

Domain randomization and generative models for robotic grasping

Domain randomization and generative models for robotic grasping. OpenAI News - artificial intelligence news.

OpenAI News Models Oct 11, 2017 👁 14

Meta-learning for wrestling

We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a…

OpenAI News Models Oct 11, 2017 👁 17

Competitive self-play

We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking,…

OpenAI News Models Sep 29, 2017 👁 19

Nonlinear computation in deep linear networks

Nonlinear computation in deep linear networks. OpenAI News - artificial intelligence news.

OpenAI News Models Sep 14, 2017 👁 18

Learning to model other minds

We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers…

OpenAI News Models Sep 13, 2017 👁 16

Learning with opponent-learning awareness

Learning with opponent-learning awareness. OpenAI News - artificial intelligence news.

OpenAI Models Aug 16, 2017 👁 13

More on Dota 2

Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far…

OpenAI News Models Aug 3, 2017 👁 17

Gathering human feedback

RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback…

OpenAI News Models Jul 27, 2017 👁 17

Better exploration with parameter noise

We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently…

OpenAI News Models Jul 20, 2017 👁 19

Proximal Policy Optimization

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which…

OpenAI News Models Jul 17, 2017 👁 24

Robust adversarial inputs

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and…

OpenAI News Models Jul 5, 2017 👁 18

Hindsight Experience Replay

Hindsight Experience Replay. OpenAI News - artificial intelligence news.

OpenAI News Models Jul 1, 2017 👁 20

Teacher–student curriculum learning

Teacher–student curriculum learning. OpenAI News - artificial intelligence news.

OpenAI News Models Jun 28, 2017 👁 22

Faster physics in Python

We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine,…

OpenAI News Models Jun 13, 2017 👁 18

Learning from human preferences

One step towards building safe AI systems is to remove the need for humans to write goal functions, since…

OpenAI News Models Jun 8, 2017 👁 19

Learning to cooperate, compete, and communicate

Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent…

OpenAI News Models Jun 5, 2017 👁 22

UCB exploration via Q-ensembles

UCB exploration via Q-ensembles. OpenAI News - artificial intelligence news.