论文标题

DeepMind Lab2d

DeepMind Lab2D

论文作者

Beattie, Charles, Köppe, Thomas, Duéñez-Guzmán, Edgar A., Leibo, Joel Z.

论文摘要

我们提出了DeepMind Lab2D,这是一种可扩展的人工智能研究环境模拟器,促进了研究人员主导的环境设计实验。 DeepMind Lab2D是根据多代理Deep Genforcement学习研究人员的特定需求而构建的,但它也可能超出该特定子领域。

We present DeepMind Lab2D, a scalable environment simulator for artificial intelligence research that facilitates researcher-led experimentation with environment design. DeepMind Lab2D was built with the specific needs of multi-agent deep reinforcement learning researchers in mind, but it may also be useful beyond that particular subfield.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源