So after looking at Pluribus poker hand ranges at all positions and Pluribus bet sizes, what learnings do we really get ?
So let’s look at the rfi frequencies actually played by the 10 pros and Pluribus on the course of 10k hands. Bear in mind these are the frequencies actually played, so slightly different from the actual ranges (although very close) ie when Pluribus gets dealt a lot more JT than 32, it does have an impact on the frequency. So not the same numbers that I’ve shown in the ranges.
Nothing out of the ordinary here, except the small variations between players show there is not yet a full concensus on rfi preflop ranges, but I think this is coming soon. Basically the Pluribus poker hands opened ranges are very close to snowie or upswing poker ranges, so this will converge.
Key Learnings RFI Strategy from Pluribus Poker Hands
- Ranges don’t change much, review, fine tune ever so slightly, add a few Kxs early.
- Randomise bet sizes, check the charts for actual sizes per position, nothing too complicated. 50% 2BB, the rest split between 2.25 and 2.5. Exception from BU with more 2.25 and 2. 5 than 2BB.
- From the SB, 63%range, then 50/50 limp/bet, and same split between bet sizes.
- Once in a blue moon for fun, bet 3, 3.5 or even 4BB. Any handx doesn’t matter.
- Not saying this is what we should do, just the poker hands Pluribus plays and their bet sizes, but if past history is anything to go by, decent players will move that way.
Pluribus is a computer poker player using artificial intelligence built by Facebook's AI Lab and Carnegie Mellon University. Pluribus plays the poker variation no-limit Texas hold 'em and is 'the first bot to beat humans in a complex multiplayer competition'.[1]
According to the Pluribus creators, 'Developing a superhuman AI for multiplayer poker was the widely recognized main remaining milestone' in computer poker prior to Pluribus. Pluribus relies on offline self-play to build a base strategy, but then continues to learn in real-time during its online play. The base strategy was computed in eight days, and at market rates would cost about $144 to produce, much smaller than contemporary superhuman game-playing milestones such as AlphaZero. In AI, two-player zero-sum games (such as heads-up hold'em) are usually won by approximating a Nash equilibrium strategy; however, this approach does not work for games with three or more players. Pluribus instead uses an approach which lacks strong theoretical guarantees, but nevertheless appears to work well empirically at defeating human players. Across the competitions, Pluribus won an average of over 30 milli big blinds per game. Pluribus' self-learned play style eschews 'limping' (calling the big blind), and engages in 'donk betting' (ending a round with a call and starting the next round by betting) more often than human experts do.[2]
Pluribus Poker Science
Researchers say they have designed a bot called Pluribus capable of taking on poker professionals in the most popular form of poker and winning. Four-time World Poker Tour title holder Darren Elias. Carnage Mellon University published in Science magazine the 10 000 poker hands played by Pluribus in 6 max no limit holdem against 10 pros. Indeed the impact is so important that the researchers have. Help me by pressing the like button!Buy me a coffee: see some of the biggest pots played by Pluribus, the AI poker bot.Plu. Pluribus takes position in consideration a lot Cbet out of position is 41% (Edited) Warning: all 25% bets are on 3bet pot, never used on single raised pot. This is not what Pluribus found to be optimal, it is a strategy of the researchers to limit CPU resource/time on single raised pots flops.
Texas Holdem Ai
Among expert poker players, Jason Les stated he felt 'very hopeless. You don't feel like there’s anything you can do to win.' Chris Ferguson stated 'Pluribus is a very hard opponent to play against. It's really hard to pin him down on any kind of hand.' Jimmy Chou stated 'Whenever playing the bot, I feel like I pick up something new to incorporate into my game.' In The Wall Street Journal, science editor Daniela Hernandez characterized Pluribus as 'advanced at a key human skill — deception'.[3][4]
Following the victory, the developers declined to release the source code, out of fear it would be misused to surreptitiously cheat against human poker players in online matches.[5][6]
References[edit]
Pluribus Poker Bot
- ^Solly, Meilan. 'This Poker-Playing A.I. Knows When to Hold 'Em and When to Fold 'Em'. Smithsonian.
- ^Brown, Noam; Sandholm, Tuomas (30 August 2019). 'Superhuman AI for multiplayer poker'. Science. 365 (6456): 885–890. doi:10.1126/science.aay2400.
- ^Vincent, James (11 July 2019). 'Facebook and CMU's 'superhuman' poker AI beats human pros'. The Verge. Retrieved 4 February 2021.
- ^Hernandez, Daniela (11 July 2019). 'Computers Can Now Bluff Like a Poker Champ. Better, Actually'. Wall Street Journal. Retrieved 4 February 2021.
- ^Ouellette, Jennifer (July 11, 2019). 'Facebook AI Pluribus defeats top poker professionals in 6-player Texas Hold 'em'. Ars Technica.
- ^Knight, Will. 'Facebook's new poker-playing AI could wreck the online poker industry—so it's not being released'. MIT Technology Review.
