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.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
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.
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.
arXiv:2607. 18488v1 Announce Type: cross Abstract: Reinforcement learning (RL) research has demonstrated success in both physical and simulated domains; however, the predominant methodology remains rooted in simulations.
We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.
arXiv:2607. 00836v1 Announce Type: cross Abstract: World models are increasingly used in embodied intelligence and generative simulation, yet their scope remains ambiguous across communities.