AI 精选动态
智能评分 70
ENPIRE 让 Codex 代理机器人在物理世界中自我学习
AI 推荐理由
此实验首次将自我学习代理应用于真实硬件，并揭示了机器人物理扩展性提升的实验数据，值得进一步探索。核心解读
OpenAI 推出 ENPIRE，将 8 只 Codex 代理与机器人、GPU 进行配对，并提供巨量令牌预算，要求它们在保持安全的前提下快速完成任务。机器人开始自主寻找视觉线索、重置场景、练习新技巧、改进控制栈、在线阅读论文、辩论、反思、停滞求助并直接在硬件上重试，完成了绳索绑扎、细小物件整理以及 GPU 安装等高精度任务。实验显示并行运行的 8 只机器人在物理扩展性上远优于更少数量的机器人。
全文
Today, we enable AutoResearch in the physical world for the first time! Introducing ENPIRE: we give 8 Codex agents a fleet of robots, an allocation of GPUs, and generous token budget. We set them free with a simple goal: solve the task as quickly as possible, keep the robots busy but stay safe, don't waste precious compute. Make no mistake.
Then humans step aside and our watch begins. The robot fleet starts to come alive: they learn to look for visual clues, reset the scene, practice novel skills, tinker with control stack, read papers online, debate, reflect, get stuck, and try again directly on the hardware. All we did is to give Codex an API to the world of atoms, and the rest is emergence.
ENPIRE is able to solve high-precision tasks like tying zip-ties, organizing fine pins, and installing GPUs all by itself. We also discovered a new type of "physical scaling": 8 robots exploring in parallel improves significantly faster than fewer ones.
A part of our NVIDIA GEAR lab now self-improves tirelessly over night. We just read the reports in the morning.
/goal: we all take a holiday and Jensen wouldn't even notice ;)
We will be open-sourcing everything, so you can host your self-running robot lab at home too! Deep dive in the thread:
https://video.twimg.com/amplify_video/2066910077886570496/vid/avc1/1920x1080/Wn1aQDpM58idppBt.mp4?tag=28