PROBĚHLO – 30. 3. 2017 – Artificial Intelligence Goes All-In: Computers Playing Poker
30.3. přijede do Prahy na veřejnou přednášku profesor Michael Bowling, vedoucí Computer Poker Research Group z University of Alberta, který bude přednášet o Umělé inteligenci a teorii her – pokeru na Fakultě elektrotechnické. Bowlingův mezinárodní tým, jehož součástí byli i výzkumníci z Katedry počítačů, FEL ČVUT a Katedry aplikované matematiky, MFF UK, vyvinul počítačový program DeepStack, který v prosinci 2016 poprvé v historii porazil profesionální hráče v jedné z nejpopulárnějších karetních her na světě – dvouhráčovém no-limit Texas hold’em pokeru. Vědecké objevy, které vedly k tomto výsledku, publikuje Science, jeden z nejprestižnějších vědeckých časopisů.
Termín: 30.3.2017, 16:00 hod
Místo: KN:E-107, Karlovo nám. 13, FEL, ČVUT
Pořadatelé: Katedra počítačů, FEL ČVUT a Katedra aplikované matematiky, MFF UK
https://www.facebook.com/events/1379837618733928/
Annotation:
Artificial intelligence has seen several breakthroughs in recent years, with games such as checkers, chess, and go often serving as milestones of progress. Poker is another game entirely, with players having their own asymmetric information about what’s happening in the game. In this talk, I’ll describe a decade long research program to build AI that can cope with the hallmarks of poker — deception, bluffing, and manipulating what other players know. This research has culminated in two landmark results: Cepheus playing a perfect game of limit poker, and most recently DeepStack (in a collaboration with Czech researchers) beating poker pros at the game of no-limit poker. These two computer programs take very different approaches, and shed light on what is required to play a game at an expert-level and what is required to play it perfectly.
About professor Michael Bowling:
- World-famous expert on AI and reinforcement learning
- Led many outstanding computer poker results:
- Polaris, beating pros in heads-up limit poker
- Cepheus, playing optimally heads-up limit poker
- DeepStack, beating pros in heads-up no-limit
- Two publications on poker in prestigious Science
- Proposed Atari games as a benchmark for AI
- Won one of the first RoboCup challenges