帖子
勋章
关注
任务
人工智能在多角色游戏中获胜
Artificial intelligence masters multiplayer poker
This year, an artificial intelligence (AI) program beat some of the world’s best players in the most popular version of poker, no-limit Texas Hold ’em. The landmark result marks the first time AI has prevailed in a multiplayer contest in which players have only imperfect information about the state of the game.
AI has been trouncing humans in games at a spectacular rate. In 2007, computer scientists developed a program guaranteed not to lose at checkers. In 2016, another team developed an AI program that defeated the best humans at Go, a board game with vastly more configurations than checkers.
Poker presents a stiffer challenge, as players cannot see their opponents’ cards and thus have limited information. In 2017, computer scientists developed an AI program unbeatable at a two-player version of Hold ’em—in which each player forms a hand from five cards laid face up on the table and two more each holds privately.
Now, AI has bested world-class players in the full multiplayer game, as computer scientists at Carnegie Mellon University in Pittsburgh, Pennsylvania, announced in August. By playing 1 trillion games against itself, their program, Pluribus, developed a basic strategy for various kinds of situations—say, playing for an inside straight. For each specific hand, it could also think through how the cards would likely play out. In 20,000 hands with six players it outperformed 15 top-level players, as measured by average winnings per hand.
Pluribus played differently from programs for two-player games. Those programs sought out a no-lose strategy, known as a Nash equilibrium, which guarantees that, on average, their opponents would do worse unless they also played with the exact same strategy. With multiple opponents, there is no such guarantee, so Pluribus simply learned what was most effective in a given situation. The program also taught itself to play while running on a single server with 64 processors—whereas the Go-playing program required more than 1200 processors.
AI developers aren’t done playing games. In poker there’s still room for improvement. Although Pluribus can bluff, it cannot adapt its strategy to exploit an opponent’s particular weaknesses. Some more complex games such as contract bridge remain unmastered. Still, the most famous objective in the application of AI to games has fallen to the computers. It may be time humans cashed in their chips.
《科学》杂志公布2019年十大科学突破 这张照片“主角”是室女座超巨椭圆星系M87中心的超大质量黑洞，由包括中国天文学家在内的200多名科研人员历时多年、从四大洲8个观测点“捕获”。 另外9个年度科学突破是： 青藏高原的古人类：中国、德国等研究人员发现，在青藏高原一处洞穴内发现的人类下颌骨化石属于丹尼索瓦人，表明早在16万年前，这种早期智人已出现在青藏高原并适应了那里的高海拔环境。 谷歌宣称成功演示“量子霸权”：谷歌称一个由53个有效量子比特组成的处理器用约200秒完成传统超级计算机约1万年才能完成的任务，但业界对此存疑。 改善儿童营养不良：肠道微生物不够成熟，导致营养不良的儿童在补充营养后仍难以恢复。研究发现，一种由鹰嘴豆、香蕉、大豆和花生粉组成的补充剂可改善肠道微生物。 “小行星撞地球”新证据：从墨西哥近海海底撞击坑采集的岩石，“记录”了6500万年前小行星撞击地球后的“糟糕一天”。 迄今探测的最遥远太阳系天体：“新视野”号探测器拍下了“阿罗科斯”（曾用名“天涯海角”）的图像，有望提供太阳系起源和演化的线索。 古生菌或为人类终极祖先：日本科学家在一种培育的古生菌中发现了此前被认为仅在真核生物中存在的基因，为研究人类的终极祖先提供线索。 囊性纤维化新药获批：美药管局批准治疗囊性纤维化的新药Trikafta，但每年超过30万美元的药费令人生畏。 抗击埃博拉病毒：两种试验性新药可将埃博拉出血热患者的存活率提升到大约70%，其中血液中病毒含量较低的患者存活率可提升到90%。 人工智能在多角色游戏中获胜：人工智能Pluribus在六人桌德州扑克比赛中击败多名世界顶尖选手，突破了人工智能仅能在国际象棋等二人游戏中战胜人类的局限。 分享到：
|
最新评论
-
mang2004 2019-12-23 23:45
-
bairuizheng 2019-12-24 00:07囊性纤维化新药获批：美药管局批准治疗囊性纤维化的新药Trikafta，但每年超过30万美元的药费令人生畏。
这药估计极少人能用得起
-
tassy 2019-12-24 03:32早期智人已出现在高原并适应了那里的高海拔环境。
-
dushunli 2019-12-24 04:532019年十大科学突破！
-
刘明欢聪慧 2019-12-24 06:10人工智能Pluribus在六人桌德州扑克比赛中击败多名世界顶尖选手，突破了人工智能仅能在国际象棋等二人游戏中战胜人类的局限。
-
likaihit 2019-12-24 06:40真牛逼啊
-
redplum 2019-12-24 06:41友谊爱
-
从业者007 2019-12-24 08:012019年TOP10科学突破
-
songyang1169 2019-12-24 08:05这张照片“主角”是室女座超巨椭圆星系M87中心的超大质量黑洞，由包括中国天文学家在内的200多名科研人员历时多年、从四大洲8个观测点“捕获”
-
stoutman 2019-12-24 08:14人工智能在多角色游戏中获胜：人工智能Pluribus在六人桌德州扑克比赛中击败多名世界顶尖选手，突破了人工智能仅能在国际象棋等二人游戏中战胜人类的局限。