We're releasing Safety Gym, a suite of environments and tools for measuring progress towards reinforcement learning agents which respect safety constraints while training.
We've trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
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
Faster Physics in Python
Learning from Human Preferences
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.