Achieving a milestone in artificial intelligence (AI) by moving beyond settings involving only two players, researchers present an AI that can outperform top human professionals in six-player no-limit Texas hold'em poker, the most popular form of poker played today. This system is the only AI to have bettered professional poker players at this multi-player game. In recent years, researchers have reported great strides in artificial intelligence. Often, games serve as challenge problems, benchmarks, and milestones for this progress. Past successes in such benchmarks, including in poker, have largely been limited to two-player games, however - even as poker in particular is traditionally played with more than two players. Multi-player games present fundamental additional issues for AI beyond those in two-player games. Here, applying approaches including "action abstraction" and "information abstraction" to overcome some of these issues, and in particular to reduce the number of different actions the AI needs to consider, Noam Brown and Tuomas Sandholm developed a program - dubbed Pluribus - that learned how to play six-player no-limit Texas hold'em by playing against five copies of itself. When pitted against five elite professional poker players, or with five copies of Pluribus playing against one professional, the computer performed significantly better over 10,000 hands of poker. Pluribus confirms the conventional human wisdom, say the authors, that limping (calling the "big blind" rather than folding or raising) is suboptimal for any player except the "small blind" player who already has half the big blind in the pot by the rules, and thus has to invest only half as much as the other players to call. The findings will be published during the week the 50th Edition of the World Series of Poker Main Event begins.