Researchers propose paradigm that trains AI agents through evolution

http://feedproxy.google.com/~r/venturebeat/SZYF/~3/1fV8YZdJBDY/

A paper published by researchers at Carnegie Mellon University, San Francisco research firm OpenAI, Facebook AI Research, and the University of California, Berkeley, and Shanghai Jiao Tong University describes a paradigm that scales up multi-agent reinforcement learning, where AI models learn by having agents interact within an environment such that the agent population increases in size over time.  » ….