Universe allows an AI agent to use a computer like a human does: by looking at screen pixels and operating a virtual keyboard and mouse. We must train AI systems on the full range of tasks we expect them to solve, and Universe lets us train a single agent on any task a human can complete with a computer. In April, we launched Gym, a toolkit for developing and comparing reinforcement learning (RL)
![Universe](https://cdn-ak-scissors.b.st-hatena.com/image/square/84f91f712b20cd5803e951a4b8f46fa11aefad9c/height=288;version=1;width=512/https%3A%2F%2Fimages.openai.com%2Fblob%2F4f73fc03-7c86-40ad-a84f-680decb21582%2Funiverse.jpg%3Ftrim%3D0%252C53%252C0%252C0%26width%3D1000%26quality%3D80)