Search AI News
Find articles from 100+ AI sources
Found 2,685 results for "OpenAI"
How AI training scales
We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability…
Quantifying generalization in reinforcement learning
We’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to…
Spinning Up in Deep RL
We’re releasing Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a…
Learning concepts with energy functions
We’ve developed an energy-based model that can quickly learn to identify and generate instances of…
Plan online, learn offline: Efficient learning and exploration via model-based control
Plan online, learn offline: Efficient learning and exploration via model-based control. OpenAI News -…
Reinforcement learning with prediction-based rewards
We’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement…
Learning complex goals with iterated amplification
We’re proposing an AI safety technique called iterated amplification that lets us specify complicated…
FFJORD: Free-form continuous dynamics for scalable reversible generative models
FFJORD: Free-form continuous dynamics for scalable reversible generative models. OpenAI News - artificial…
The International 2018: Results
OpenAI Five lost two games against top Dota 2 players at The International in Vancouver this week,…
Large-scale study of curiosity-driven learning
Large-scale study of curiosity-driven learning. OpenAI News - artificial intelligence news.
Learning dexterity
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
Variational option discovery algorithms
Variational option discovery algorithms. OpenAI News - artificial intelligence news.
Glow: Better reversible generative models
We introduce Glow, a reversible generative model which uses invertible 1x1 convolutions. It…
Learning Montezuma’s Revenge from a single demonstration
We’ve trained an agent to achieve a high score of 74,500 on Montezuma’s Revenge from a single human…
Retro Contest: Results
The first run of our Retro Contest—exploring the development of algorithms that can generalize from…
Learning policy representations in multiagent systems
Learning policy representations in multiagent systems. OpenAI News - artificial intelligence news.
Improving language understanding with unsupervised learning
We’ve obtained state-of-the-art results on a suite of diverse language tasks with a scalable, task-agnostic…
GamePad: A learning environment for theorem proving
GamePad: A learning environment for theorem proving. OpenAI News - artificial intelligence news.
AI and compute
We’re releasing an analysis showing that since 2012, the amount of compute used in the largest AI training…
AI safety via debate
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human…
Evolved Policy Gradients
We’re releasing an experimental metalearning approach called Evolved Policy Gradients, a method that…
Gotta Learn Fast: A new benchmark for generalization in RL
Gotta Learn Fast: A new benchmark for generalization in RL. OpenAI News - artificial intelligence news.
Retro Contest
We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to…
Variance reduction for policy gradient with action-dependent factorized baselines
Variance reduction for policy gradient with action-dependent factorized baselines. OpenAI News - artificial…