2006 AAAI Computer Poker Competition Michael Littman Rutgers

2006 AAAI Computer Poker Competition Michael Littman Rutgers University Martin Zinkevich Christian Smith Luke Duguid U of Alberta

What is Poker? • The OR View – A partial information game with over 1018 states. • The AI View – A huge opponent modeling challenge. • The Public View – Really popular! Lots of fun!

What is the Game? • Play 1000 hands of Heads-up Limit Texas Hold’em Poker against an opponent • Reset bots, switch seats, and play again with the same hands. – lower variance – more fair • Repeat 6 -20 times – Can treat the outcome of the duplicate match as a random variable which we have sampled several times.

How do you win? • Make money! • Bankroll Competition – Against overall, have the maximum total bankroll – Highlights opponent modeling and learning • Series Competition – Against individuals, have positive bankroll – Highlights the OR problem of “solving” the game

The Teams • Hyperborean: University of Alberta Edmonton, Canada • Bluffbot: Finland • Monash: Monash University, Australia • Teddy: USA • Gs 2: Carnegie Mellon University, Pittsburgh, USA

Before I Begin • There is a period that is allocated for competitors to contest the results that has yet to expire.

Bankroll Results Competitor Winnings (small bets/hand) Teddy (USA) -0. 4616 sb/h

Bankroll Results Competitor Winnings (small bets/hand) Monash (Monash U. , Australia) Teddy (USA) -0. 0273 sb/h -0. 4616 sb/h

Bankroll Results Competitor Winnings (small bets/hand) Bluffbot (Finland) Monash (Monash U. , Australia) Teddy (USA) 0. 0954 sb/h -0. 0273 sb/h -0. 4616 sb/h

Bankroll Results Competitor Hyperborean (U. Alberta) Bluffbot (Finland) Monash (Monash U. , Australia) Teddy (USA) Winnings (small bets/hand) 0. 3935 sb/h 0. 0954 sb/h -0. 0273 sb/h -0. 4616 sb/h

Bankroll-Heads Up Hyperborean (U Alberta) Bluffbot (Finland) Monash (Monash U) Teddy (USA) Hyperborean Wins Bluffbot Wins Teddy Wins Bluffbot (Finland) Hyperborean Wins Monash (Monash U) Hyperborean Wins Bluffbot Wins Teddy (USA) Hyperborean Wins Teddy Wins Monash Wins

Bankroll-Heads Up (Small Bets/Hand) Hyperborean (U Alberta) Bluffbot (Finland) Monash (Monash U) Teddy (USA) 0. 0514 ± 0. 0171 0. 7227 ± 0. 0161 0. 4067 ± 0. 0247 0. 5271 ± 0. 0197 -0. 1895 ± 0. 0289 Bluffbot (Finland) -0. 0514 ± 0. 0171 Monash (Monash U) -0. 7227 ± 0. 0161 -0. 5271 ± 0. 0197 Teddy (USA) -0. 4067 ± 0. 0247 0. 1895 ± 0. 0289 1. 1678 ± 0. 0427 -1. 1678 ± 0. 0427

Bankroll-Overall Significance • Difference between Bluffbot and U of Alberta • 0. 2982 small bets/hand • 0. 0190 standard deviations

The Most Interesting Result • In the bankroll competition, in head-tohead, Bluff. Bot beat Monash who beat Teddy who beat Bluff. Bot • A practical example of the non-transitivity of poker

Results-Series (Small Bets/Hand) Hyperborean (U Alberta) Bluffbot (Finland) Gs 2 (CMU) Monash (Monash U) Winner: Hyperborean Winner: Bluffbot (Finland) Winner: Hyperborean Gs 2 (CMU) Winner: Hyperborean Winner: Bluffbot Monash (Monash U) Winner: Hyperborean Winner: Bluffbot Winner: Gs 2

Results-Series (Small Bets/Hand) Hyperborean (U Alberta) Bluffbot (Finland) Gs 2 (CMU) Monash (Monash U) 0. 1145 ± 0. 0375 0. 1843 ± 0. 0079 0. 7344 ± 0. 029 0. 1200 ± 0. 0561 0. 5214 ± 0. 0408 Bluffbot (Finland) -0. 1145 ± 0. 0375 Gs 2 (CMU) -0. 1843 ± 0. 0079 -0. 1200 ± 0. 0561 Monash (Monash U) -0. 7344 ± 0. 029 -0. 5214 ± 0. 0398 0. 6512 ± 0. 0397 -0. 6512 ± 0. 0398

Things to Never Assume • All bots will work on the competition machines the first time • The server code is bug-free • Everybody has a common idea of the rules of poker (or even heads-up Texas Hold’em) • People can write code instantaneously

Exhibitionary Aspects of the Competition • Bots submitted late • Bots debugged after the deadline • The time limit was very large for the series competition

Maybe Next Year • More advance notice • Competitors need access to one of the machines they will use • Server code needs to be frozen before the competition begins • More variants of poker need to be included, especially: – >2 players – >1000 hands • There has to be a 7 sec/hand time limit

Is Poker “Solved”? • No one has ever solved a four-round abstraction of poker without a partition into the early game and the late game. • The game of poker is also about your opponent. For instance, playing rock-paper -scissors against a four-year-old is different than against an adult.

Next Year • This summer: write the rules • This winter: write the code • Next summer: next competition

Are You Interested? • Come talk to us • maz@cs. ualberta. ca • bowling@cs. ualberta. ca

Summary • The poker competition brought together five teams in two competitions. • The competition was very close, and very interesting, non-transitive (A beats B beats C beats A) performance was observed. • A freeware codebase was developed for future competitions.