How good are the BEST poker bots right now at holdem with more than two players?
CMU's Libratus builds substantial lead in Brains vs. AI competition
51–60 of 123 posts
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#52Is this really fair? Part of Poker is "reading" when other players are bluffing, it's a lot more challenging to read when a computer is...
First of all, that's not true. Most players play several tables at the same time against the same player, up to four heads-up. That's something like 600 hands an hour in HU.
There's little heads-up play in live games, other than at the end of the tournament, and the stack sizes are completely different. These are not tournament players, they're heads-up specialists. They most assuredly play online the majority of the time.
Second of all, the computer doesn't read the human players, why would it matter? It's all up to actual strategies at that point.
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#53Libratus biggest edge is probably grinding away at their blunders & tendencies (eg. Don never check raise bluffs in this spot, so I can safely value bet). It would be really interesting if they published the bots results vs. a mythical generic player. The difference would be a nice estimate as to how big an edge it derives from backtesting it's personalization strategies.
It doesn't use player tendencies, it plays closer to Nash equilibrium than the human players, AFAIK.
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#54Earlier quoted context omitted.
Why is it unfair? Both the human and computer players are unable to make reads on the other based on physical cues.
It's not that it's unfair, it's just a considerably different game than human vs. human poker. It would, however, be very interesting to see if the software can reveal exploitable tendencies in the players' behavior that even other top players would be unlikely to discover.
> It's not that it's unfair, it's just a considerably different game than human vs. human poker.
absolutely not, these players play online, there are no tells online
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#55Honestly, this doesn't look to be a true test of who is better at poker. Poker is not like chess - a lot of emotions are involved in reading another players' cues (if he is touching his face, whether he is talking nervously, how quickly does he call all in etc.). Making all this computerized seems to take the spirit of poker away. It is like playing online poker which is an entirely different ball game vs. real poker…
> It is like playing online poker which is an entirely different ball game vs. real poker.
These are online players. They're playing the game they are best at.
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#56Easy with 16 tetra of ram
And tanking for 1+ mins on turn and river decisions (it would time out in real online poker). And $10M in computer resources. But impressive nonetheless.
There's a time bank online. If the time bank were too short, they could just spend $20M instead to make decisions twice as fast.
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#57I believe we are witnessing the Cambrian explosion of intelligences. The techniques behind Libratus (abstraction algorithm and game theory [1]) appear to be qualitatively distinct from those behind AlphaGo (deep reinforcement learning and MCMC) and DeepBlue (search and heuristics). An ecology of Artificial Intelligences, unbounded by our evolutionary history and neural architecture, could evolve to suit each particul…
> Promises and perils abound.
what's the peril? I can only see promise ahead, if AI's progress continue unimpeded.
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#58I believe we are witnessing the Cambrian explosion of intelligences. The techniques behind Libratus (abstraction algorithm and game theory [1]) appear to be qualitatively distinct from those behind AlphaGo (deep reinforcement learning and MCMC) and DeepBlue (search and heuristics). An ecology of Artificial Intelligences, unbounded by our evolutionary history and neural architecture, could evolve to suit each particul…
Chess, Go, Poker... All feel like variations on the same theme. While it's obvious there is innovation being done, I want to see something more challenging. Something with more dimensionality and integration of several types of input.
How about a machine that can beat someone at Smash Bros, a game with varied characters, complex comboing mechanics, and a nontrivial computer vision task?
Or--more difficult by a few orders of magnitude--what about a robot that can beat someone at tennis? Or a team of robots that can best a professional basketball team?
When do you suppose we'll begin to see these sorts of things? Within our lifetime, I hope?
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#59I believe we are witnessing the Cambrian explosion of intelligences. The techniques behind Libratus (abstraction algorithm and game theory [1]) appear to be qualitatively distinct from those behind AlphaGo (deep reinforcement learning and MCMC) and DeepBlue (search and heuristics). An ecology of Artificial Intelligences, unbounded by our evolutionary history and neural architecture, could evolve to suit each particul…
Chess, Go, Poker... All feel like variations on the same theme. While it's obvious there is innovation being done, I want to see something more challenging. Something with more dimensionality and integration of several types of input. How about a machine that can beat someone at Smash Bros, a game with varied characters, complex comboing mechanics, and a nontrivial computer vision task? Or--more difficult by a few or…
Smash bros shouldn't be too hard. Reflexes alone would give the CPU an enormous advantage.
Re: CMU's Libratus builds substantial lead in Brains vs. AI competition
#60Earlier quoted context omitted.
This is not neural net. It uses an algorithm called counterfactual regret minimization to compute the Nash equilibrium of the game, no data required.
what about - https://arxiv.org/abs/1701.01724
That's a new bot by university of alberta. Funnily enough, even that doesn't require actual data. It uses randomly generated ones.