Skip to main content
Join Community

Search AI Workflow Pro

Search tools, categories, stacks, and pages

Fresh daily

AI News

Latest AI tool releases, research breakthroughs, and industry news.

AllReleasesResearchFundingTutorialsOpinion

Older

Equivalence between policy gradients and soft Q-learning

OpenAI Blog·Apr 21research

Stochastic Neural Networks for hierarchical reinforcement learning

OpenAI Blog·Apr 10research

Unsupervised sentiment neuron

We’ve developed an unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.

OpenAI Blog·Apr 6research

Spam detection in the physical world

We’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.

OpenAI Blog·Apr 1research

Evolution strategies as a scalable alternative to reinforcement learning

We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e.g. Atari/MuJoCo), while overcoming many of RL’s inconveniences.

OpenAI Blog·Mar 24research

One-shot imitation learning

OpenAI Blog·Mar 21research

Learning to communicate

In this post we’ll outline new OpenAI research in which agents develop their own language.

OpenAI Blog·Mar 16research

Emergence of grounded compositional language in multi-agent populations

OpenAI Blog·Mar 15research

Prediction and control with temporal segment models

OpenAI Blog·Mar 12research

Third-person imitation learning

OpenAI Blog·Mar 6research

Attacking machine learning with adversarial examples

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this post we’ll show how adversarial examples work across different mediums, and will discuss why securing systems against them can be difficult.

OpenAI Blog·Feb 24research

Adversarial attacks on neural network policies

OpenAI Blog·Feb 8research

PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications

OpenAI Blog·Jan 19research

Faulty reward functions in the wild

Reinforcement learning algorithms can break in surprising, counterintuitive ways. In this post we’ll explore one failure mode, which is where you misspecify your reward function.

OpenAI Blog·Dec 21research

#Exploration: A study of count-based exploration for deep reinforcement learning

OpenAI Blog·Nov 15research

OpenAI and Microsoft

We’re working with Microsoft to start running most of our large-scale experiments on Azure.

OpenAI Blog·Nov 15research

On the quantitative analysis of decoder-based generative models

OpenAI Blog·Nov 14research

A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models

OpenAI Blog·Nov 11research

RL²: Fast reinforcement learning via slow reinforcement learning

OpenAI Blog·Nov 9research

Variational lossy autoencoder

OpenAI Blog·Nov 8research