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.
Research
Research
Roboschool
We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.
Research
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.
Uncategorised
Why Momentum Really Works
We often think of optimization with momentum as a ball rolling down a hill. This isn’t wrong, but there is much more to the story.
Research
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.
Research
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…
Uncategorised
Research Debt
Science is a human activity. When we fail to distill and explain research, we accumulate a kind of debt…