Photo credit: The Verge
First, OpenAI’s bots were trained to defeat human opponents in DOTA 2 (bottom video), now, Google’s DeepMind AI has exceeded human-level gameplay in Quake 3. The DeepMind agents go into the game without any instructions, and then start competing against themselves until they develop winning strategies – an AI agent plays against an identical clone. Well, the research team went above and beyond by training 30 agents in different play styles. It took nearly half a million matches each lasting five minutes, to train the agents to exceed human-level gameplay. Click here for the first image in today’s viral picture gallery. Continue reading for the five most popular viral videos today, including one ten life hacks for summer.
