SEOUL — In a milestone, Google DeepMind’s AlphaGo program defeated legendary Go player Lee Sedol in the first game of a five-match series on Wednesday.

Lee, a 9-dan professional considered one of the greatest Go players of the modern era, resigned after about three and a half hours with 28 minutes and 28 seconds remaining on his clock. The series is the first time a professional 9-dan Go player has taken on a computer, and Lee is competing for a $1 million prize.

“I was very surprised. I didn’t expect to lose,” Lee said after the game. He admitted being in shock but said he enjoyed the game and looked forward to the next. DeepMind founder Demis Hassabis called it a “hugely exciting” and “very tense” game, while team lead David Silver said it pushed AlphaGo to its limits.

The AI’s unorthodox moves, particularly in the opening, caught Lee off guard. Go has long been a major AI challenge because the high level of intuition and evaluation required makes it hard for computers to crack. DeepMind’s AlphaGo uses a complex system of deep neural networks and machine learning. Lee will face off against AlphaGo again tomorrow and on Saturday, Sunday, and Tuesday.