Slashdot Mirror


DeepMind's AI Agents Exceed 'Human-Level' Gameplay In Quake III (theverge.com)

An anonymous reader quotes a report from The Verge: AI agents continue to rack up wins in the video game world. Last week, OpenAI's bots were playing Dota 2; this week, it's Quake III, with a team of researchers from Google's DeepMind subsidiary successfully training agents that can beat humans at a game of capture the flag. DeepMind's researchers used a method of AI training that's also becoming standard: reinforcement learning, which is basically training by trial and error at a huge scale. Agents are given no instructions on how to play the game, but simply compete against themselves until they work out the strategies needed to win. Usually this means one version of the AI agent playing against an identical clone. DeepMind gave extra depth to this formula by training a whole cohort of 30 agents to introduce a "diversity" of play styles. How many games does it take to train an AI this way? Nearly half a million, each lasting five minutes. DeepMind's agents not only learned the basic rules of capture the flag, but strategies like guarding your own flag, camping at your opponent's base, and following teammates around so you can gang up on the enemy. "[T]he bot-only teams were most successful, with a 74 percent win probability," reports The Verge. "This compared to 43 percent probability for average human players, and 52 percent probability for strong human players. So: clearly the AI agents are the better players."

1 of 137 comments (clear)

  1. Re:Bad Challenge by rtb61 · · Score: -1, Flamebait

    At the very least play with the same handicap ie watching a screen and actually manipulating a mouse and keyboard, not directly plugged in. People will also play better if they were directly plugged in. This kind of crap really is just a sales blow job for AI which is a pretty solid indication that AI is currently shite and they need to make up more shite to cover it up. Would not need to do this crap if AI where any good, rather than the current database store and sort. It's the American way though, want the big bucks, waffle bullshit, pay lobbyists, get billion dollar contracts, produce crap, use main stream media to cover it all up, shuffle the money off to tax havens and don't pay any taxes. They are crippling the US economy with fraud and corruption.

    --
    Chaos - everything, everywhere, everywhen