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.
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.
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.
arXiv:2606. 19419v1 Announce Type: cross Abstract: Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions.
arXiv:2606. 07217v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are emerging as a promising paradigm for robotic manipulation, enabling general-purpose policies trained from large corpora of demonstrations and action labels.
arXiv:2607. 00642v1 Announce Type: new Abstract: Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models.
arXiv:2602. 20220v2 Announce Type: replace-cross Abstract: We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots.