Robotics and embodied AI

Scaling robotics datasets with video encoding

Pollen-Vision: Unified interface for Zero-Shot vision models in robotics

Solving Rubik’s Cube with a robot hand

We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code as OpenAI Five paired with a new technique called Automatic Domain Randomization (ADR).

OpenAI Robotics Symposium 2019

We hosted the first OpenAI Robotics Symposium on April 27, 2019.

Learning concepts with energy functions

We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, and furthest, expressed as sets of 2d points. Our model learns these concepts after only five demonstrations.

Learning dexterity

We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.

Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research

Ingredients for robotics research

We’re releasing eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay, all developed for our research over the past year. We’ve used these environments to train models which work on physical robots.

Generalizing from simulation

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.

Asymmetric actor critic for image-based robot learning

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

Domain randomization and generative models for robotic grasping

Meta-learning for wrestling

We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent, and also show that the meta-learning agent can adapt to physical malfunction.

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.

Faster physics in Python

We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics research.

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.

Roboschool

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

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.

Team update

The OpenAI team is now 45 people. Together, we’re pushing the frontier of AI capabilities—whether by validating novel ideas, creating new software systems, or deploying machine learning on robots.

OpenAI Gym Beta

We’re releasing the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning (RL) algorithms. It consists of a growing suite of environments (from simulated robots to Atari games), and a site for comparing and reproducing results.