Uber AI plays any Atari 2600 game with 'superhuman' skill

Uber AI plays any Atari 2600 game with 'superhuman' skill 1

DeepMind isn’t the only one with an Atari-savvy AI. A team of Uber AI researchers has developed a set of algorithms, Go-Explore, that reportedly beats any Atari 2600 game with “superhuman” scores, including ones where AI previously had trouble besting its organic rivals. The key is a system that takes care to remember promising states and returns to those states before it sets out exploring.

Go-Explore saw improvement by “orders of magnitude” in some games. It was the first to beat every level in Montezuma’s Revenge, and got a “near-perfect” Pitfall score — both of these are particularly challenging for reinforcement learning systems like this. DeepMind’s Agent57 reached a similar benchmark, according to the team’s Jeff Clune, but through “entirely different methods.” That gives developers a “diversity” of approaches to the same tasks.

bitcoin
Bitcoin (BTC) $ 40,115.00
ethereum
Ethereum (ETH) $ 2,544.30
tether
Tether (USDT) $ 1.00
binance-coin
Binance Coin (BNB) $ 367.79
cardano
Cardano (ADA) $ 1.56
dogecoin
Dogecoin (DOGE) $ 0.321369
xrp
XRP (XRP) $ 0.872563
polkadot
Polkadot (DOT) $ 24.19
usd-coin
USD Coin (USDC) $ 1.00
uniswap
Uniswap (UNI) $ 23.53