Skip to main content
Get Template — $89

Search AI Workflow Center

Search tools, categories, stacks, and pages

Fresh daily

AI News

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

AllReleasesResearchFundingTutorialsOpinion

Older

Proximal Policy Optimization

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better than state-of-the-art approaches while being much simpler to implement and tune. PPO has become the default reinforcement learning algorithm at OpenAI because of its ease of use and good performance.

OpenAI Blog·Jul 20research

Robust adversarial inputs

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.

OpenAI Blog·Jul 17research

Hindsight Experience Replay

OpenAI Blog·Jul 5research

Teacher–student curriculum learning

OpenAI Blog·Jul 1research

Learning from human preferences

One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex goal, or getting the complex goal a bit wrong, can lead to undesirable and even dangerous behavior. In collaboration with DeepMind’s safety team, we’ve developed an algorithm which can infer what humans want by being told which of two proposed behaviors is better.

OpenAI Blog·Jun 13research

Learning to cooperate, compete, and communicate

Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful properties: first, there is a natural curriculum—the difficulty of the environment is determined by the skill of your competitors (and if you’re competing against clones of yourself, the environment exactly matches your skill level). Second, a multiagent environment has no stable equilibrium: no matter how smart an agent is, there’s always pressure to get smarter. These environments have a very different feel from traditional environments, and it’ll take a lot more research before we become good at them.

OpenAI Blog·Jun 8research

UCB exploration via Q-ensembles

OpenAI Blog·Jun 5research

Robots that learn

We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.

OpenAI Blog·May 16research

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