Image:Google DeepMind(X) Google DeepMind は深層強化学習(Deep RL)を使用して、小さな二足歩行ロボットにサッカーを教え、そのプレイする様子をX(Twitter)に投稿した。 Robotics has long used games like soccer to test complex motion, coordination and environment awareness. 🤖 Our agents were trained in simulation using the MuJoCo physics engine, and then transferred to small humanoid robots with 20 actuated joints. https://t.co/RFBxLG7qBV — Google DeepMin
![Google DeepMind、AI搭載の二足歩行ロボにサッカーをプレイ。シュートブロックも可能に | Gadget Gate](https://cdn-ak-scissors.b.st-hatena.com/image/square/193ecef8ba8ed32ee5cf396f39f902fd2671e1e5/height=288;version=1;width=512/https%3A%2F%2Fgadget.phileweb.com%2Fwp-content%2Fuploads%2F2024%2F04%2FGDM.jpg)