Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How much did AlphaGo Zero cost? (2018)

yuzeh.com

Post reply on HN
Print view View original

131–140 of 179 posts

Re: How much did AlphaGo Zero cost? (2018)

#131

Post by __s »

ipsum2 wrote: post #2

Alpha Go Zero*, which was trained from scratch, without human games. I've also heard rumors that AlphaStar ( https://deepmind.com/blog/article/alphastar-mastering-real-t... ) was essentially put on hold because it was too expensive to improve/train. The bot wasn't able to beat StarCraft champions and _only_ got to a grandmaster level.

https://www.youtube.com/watch?v=nbiVbd_CEIA

At the last Blizzcon they had it around. The setup wasn't ideal, so Serral (won world finals in 2018, reached semifinals in 2019) wasn't really happy with how he played, but it won

This was also a version where they'd worked on preventing its ability to micro at quadruple digit apm

Re: How much did AlphaGo Zero cost? (2018)

#132

Post by thelean12 »

sukilot wrote: post #115
nl wrote: post #107

Earlier quoted context omitted.

If by "it's far from a solved problem" you mean that chess isn't a solved game that's true. But Kasparov and others have given up on the idea that a human provides any unique insight into chess anymore. Computers are just better.

That's absurd. He works on human+chess research. He obviously hasn't given up on human insight. What he has given up on is a single human beating a computer.

Can a human + computer beat just a computer?

I can't imagine a human doing anything besides making things worse or even.

Re: How much did AlphaGo Zero cost? (2018)

#133

Post by JoeDaDude »

luisvictoria wrote: post #99
air7 wrote: post #93

Earlier quoted context omitted.

Is human&computer better than computer only?

Not really, humans barely provide insight (if anything), which chess engines don’t already consider. Deep Blue could evaluate 200 million different moves... per second. And that’s from 1997. The few and rare times an engine gets funky is usually in end-game positions where the engine can’t seem to find a sacrifice to win the game and will output a current position as drawn. These cases are few and I very much doubt t…

> ...learning completely on its own giving it nothing but the rules which is how AlphaGo works...

Not to be too picky, but it was AlphaGo _Zero_ that learned from the rules alone. AlphaGo learned from a large database of human played games: "...trained by a novel combination of supervised learning from human expert games". [1]

AlphaGo Zero, derived from AlphaGo, was "an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules". [2]

[1] https://www.nature.com/articles/nature16961

[2] https://pubmed.ncbi.nlm.nih.gov/29052630/

Re: How much did AlphaGo Zero cost? (2018)

#134

Post by skywhopper »

I'll quibble with a little bit of this.

"AlphaGo Zero showed the world that it is possible to build systems to teach themselves to do complicated tasks."

It didn't do any such thing. The game of go has a huge number of potential moves and outcomes, but the rules themselves are trivial, the board position can be measured in a handful of bytes and gameplay always and only progresses in one direction. And judging a good vs bad outcome is just a matter of comparing two numbers.

Go is challenging and interesting for humans, but it's not remotely as "complicated" as driving a car or translating a language.

Re: How much did AlphaGo Zero cost? (2018)

#135

Post by 29athrowaway »

runarberg wrote: post #123
thomasahle wrote: post #77

Earlier quoted context omitted.

I was suspecting another boring clone, but Kata looks like a cool project with nice new ideas! Thanks for sharing

KataGo is also cool for those of us that use bots to review our human games because it has score estimator. With Leela a 0.5 win and a 20.5 win in the endgame can both amount to 99.5% chance of winning, but to us (amateur) humans that is not true.

There is a Go client that is distributed with Kata Go and was built for that purpose: https://github.com/sanderland/katrain and is distributed as a pip package, making it very frictionless to install.

With a tool like this, instead of waiting for a Go pro to visit our local Go club to review our kifu, I can have my game reviewed move by move until the end (not only the first n moves).

I can still have questions for pros, but they would be more specific.

Now, playing a superhuman intelligence bot can be unfun. Now matter how much effort you put in a move, you will just keep making your outcome worse with every move.

Another important use-case is that the AI can also tell you if a joseki is actually joseki, and how to refute a bad joseki move.

Re: How much did AlphaGo Zero cost? (2018)

#137

Post by glinscott »

irjustin wrote: post #4

Alpha Go Zero inspired the development of an open source version, Leela Go Zero which Leela Chess Zero is forked from by the same guy who made Stock Fish. Lots of people contribute what I imagine are amounts of CPU Power/money to the Leela Chess Zero project[1]. Would love to see Alpha Chess vs Leela Chess. [1] https://training.lczero.org/ [edit] I've caused terrible confusion by melding Leela Go and Leela Chess when…

The great thing about these community driven efforts is that it is indeed feasible to reproduce these super expensive efforts. I'm a bystander now, as new maintainers have taken over, and they are doing a fantastic job pushing things forward.

This is also how Stockfish got to be the #1 engine. By being open source, and having the testing framework (https://tests.stockfishchess.org) use donated computer time from volunteers, it was able to make fast, continuous progress. It flipped what was previously a disadvantage (if you are open source, everyone can copy your ideas), into an advantage - as you can't easily set up a fishtest like system with an engine that isn't already developed in public.

Re: How much did AlphaGo Zero cost? (2018)

#138

Post by sharedfrog »

luisvictoria wrote: post #99
air7 wrote: post #93

Earlier quoted context omitted.

Is human&computer better than computer only?

Not really, humans barely provide insight (if anything), which chess engines don’t already consider. Deep Blue could evaluate 200 million different moves... per second. And that’s from 1997. The few and rare times an engine gets funky is usually in end-game positions where the engine can’t seem to find a sacrifice to win the game and will output a current position as drawn. These cases are few and I very much doubt t…

> I’d recommend you to look up a few games between AlphaGo and Stockfish

Agadmator's youtube channel covers a bunch of those. https://www.youtube.com/watch?v=1yM0D1iZLrg

Re: How much did AlphaGo Zero cost? (2018)

#139

Post by blueboo »

mikorym wrote: post #91
irjustin wrote: post #4

Alpha Go Zero inspired the development of an open source version, Leela Go Zero which Leela Chess Zero is forked from by the same guy who made Stock Fish. Lots of people contribute what I imagine are amounts of CPU Power/money to the Leela Chess Zero project[1]. Would love to see Alpha Chess vs Leela Chess. [1] https://training.lczero.org/ [edit] I've caused terrible confusion by melding Leela Go and Leela Chess when…

AFAIK Garry Kasparov to this day does computer&human vs. computer&human chess research, and it's far from a solved problem.

He recently spoke quite dismissively of computer- augmented chess on the Lex Friedman podcast. Essentially, the computer knows best...so computer and human isn’t meaningfully different from computer and rubber stamper.

Re: How much did AlphaGo Zero cost? (2018)

#140

Post by scheveningen »

thelean12 wrote: post #132
sukilot wrote: post #115

Earlier quoted context omitted.

That's absurd. He works on human+chess research. He obviously hasn't given up on human insight. What he has given up on is a single human beating a computer.

Can a human + computer beat just a computer? I can't imagine a human doing anything besides making things worse or even.

It's much more difficult than it used to be, but I think there is still some value to human guidance, more as a "referee" than anything else.

Right now we have essentially two top tier engines -- traditional brute force with alpha beta pruning (stockfish), and ML (leela). Both alone are incredibly strong, but they are strongest and weakest in different types of positions. A computer chess expert, who knows what kind of positions favor stockfish and what kind favor leela, could act as a "referee" between the two engines when they disagree, and when they are unanimous, simply accept the move.

Ten years ago, a grandmaster driving a single engine could typically beat an equal strength engine. I don't think that's the case anymore.

But I think if you have someone who is an expert at computer chess -- not so much a chess grandmaster, and you gave them Leela AND SF, and let them pick which one to use when in the case of conflicts -- they would score positive against either leela or stockfish in isolation.

Larry Kaufman designed his new opening repertoire book by doing exactly this -- running Leela on 2 cores + GPU, and stockfish on 6 cores, and doing the conflict resolution with his own judgement.

The human can certainly no longer pull his own moves out of thin air, though.

Post reply on HN