OpenAI Blog

Better exploration with parameter noise

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

Proximal Policy Optimization

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

Robust adversarial inputs

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

Hindsight Experience Replay

Teacher–student curriculum learning

Faster physics in Python

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

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…

Learning to cooperate, compete, and communicate

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

UCB exploration via Q-ensembles

OpenAI Baselines: DQN

We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with…

Robots that learn

We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new…

Roboschool

We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.

Equivalence between policy gradients and soft Q-learning

Stochastic Neural Networks for hierarchical reinforcement learning

Unsupervised sentiment neuron

We’ve developed an unsupervised system which learns an excellent representation of sentiment, despite being trained…

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.

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…

One-shot imitation learning

Distill

We’re excited to support today’s launch of Distill, a new kind of journal aimed at excellent communication of machine…

Learning to communicate

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

Emergence of grounded compositional language in multi-agent populations

Prediction and control with temporal segment models

Third-person imitation learning

Attacking machine learning with adversarial examples

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the…

Adversarial attacks on neural network policies

Team update

The OpenAI team is now 45 people. Together, we’re pushing the frontier of AI capabilities—whether by validating novel…

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

Faulty reward functions in the wild

Reinforcement learning algorithms can break in surprising, counterintuitive ways. In this post we’ll explore one…

Universe

We’re releasing Universe, a software platform for measuring and training an AI’s general intelligence across the…

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

OpenAI and Microsoft

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

On the quantitative analysis of decoder-based generative models

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

RL²: Fast reinforcement learning via slow reinforcement learning

Variational lossy autoencoder

Extensions and limitations of the neural GPU