AlphaZero beats AlphaGo Zero, Stockfish, and Elmo

[Leo]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

It is still unsatisfying to use that old of a SF.

[Leto]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

It is still unsatisfying to use that old of a SF.

Judging from the score of the match it wouldn't matter if the latest SF dev were used, AlphaZero should dominate it easily. And that was with just 4 hours of training. Imagine how much stronger AlphaZero is now.

[Leo]

Was it to inconvenient to download the latest SF?

Because it isn't an official release and has not been tested as exhaustively. That's the point of releases. Just take a look at the TCEC what happened to Komodo when going with a dev version.

Besides, the release has been rated in many games while the "dev version of today" has not.

It is still unsatisfying to use that old of a SF.

Judging from the score of the match it wouldn't matter if the latest SF dev were used, AlphaZero should dominate it easily. And that was with just 4 hours of training. Imagine how much stronger AlphaZero is now.

When it solves a 10 man EGTB I will agree its impressive. Maybe it can do that in 4 hours too.

[Ras]

It is still unsatisfying to use that old of a SF.

It's really not Google's fault that the Stockfish team hasn't had enough confidence to release Stockfish 9 for more than a full year.

[Leo]

It is still unsatisfying to use that old of a SF.

It's really not Google's fault that the Stockfish team hasn't had enough confidence to release Stockfish 9 for more than a full year.

I see your point. It does look like this is a chess computer revolution. Most of us new this was coming someday right?

[Ras]

It does look like this is a chess computer revolution.

I wouldn't limit this to chess. It seems that their framework is flexible enough to master chess, Go and other games, indicating that it might be suited to a wide range of tasks - by self-learning. Maybe, the AI spring is coming, after decades of winter. This could be a computer revolution.

For now, Google has a monopoly on these TPUs, and they will continue to enjoy this advantage for quite some time. That's why they don't sell them and rent them out via cloud. They're cashing in on being the first to the market.

However, market economy inevitably dictates what will happen: other big companies will jump the train, Intel and Nvidia in particular, aiming to sell that stuff to end customers. Similarly to what happened in the PC revolution.

Especially Intel actually HAS to think of a new strategy, given that their adventures to get hold in ARM's domain by and large have failed. They can't bet their whole company's future on x86. Plus that Intel has the money and the experts to achieve success, I think.

[Uri Blass]

It is still unsatisfying to use that old of a SF.

It's really not Google's fault that the Stockfish team hasn't had enough confidence to release Stockfish 9 for more than a full year.

Stockfish release a new version every few days that everybody can download and I see no reason to care about the name of the new version.

Tests show maybe 40 elo advantage for latest version and certainly not 100 elo at long time control so alphago could beat also the new version of stockfish.

[MikeB]

It is still unsatisfying to use that old of a SF.

It's really not Google's fault that the Stockfish team hasn't had enough confidence to release Stockfish 9 for more than a full year.

Stockfish release a new version every few days that everybody can download and I see no reason to care about the name of the new version.

Tests show maybe 40 elo advantage for latest version and certainly not 100 elo at long time control so alphago could beat also the new version of stockfish.

That's true but I believe Google purposely choose a weaker version for impact. This is not about chess, this about selling their AI packages to Cities and Governments, the more dominating the result , the bigger the headline - free advertising. Even the result is not as dominating as it sounds - as the relatively high draw rate keeps the ELO difference under 80 ELO, I added one win for SF otherwise Bayeselo does not compute the ELO difference correctly. Current SF would have lost but probably would have been within 30 or 40 ELO

Code: Select all

ResultSet-EloRating>x
ResultSet>reset
ResultSet>rp /Users/michaelbyrne/cluster.mfb/12052200.txt 
101 game(s) loaded
ResultSet>elo
ResultSet-EloRating>mm 
00:00:00,00
ResultSet-EloRating>confidence 0.95
0.9
ResultSet-EloRating>r
Rank Name                 Rating   Δ     +    -     #     Σ    Σ%     W    L    D   W%    =%   OppR 
---------------------------------------------------------------------------------------------------------
   1 Stronger Engine       3132   0.0   50   50   101   64.0  63.4   28    1   72  27.7  71.3  3068 
   2 Weaker Engine         3068  64.3   50   50   101   37.0  36.6    1   28   72   1.0  71.3  3132 
---------------------------------------------------------------------------------------------------------

[jhellis3]

I would say the result is much more dominating that the Elo difference would suggest. If one looks at the games, it becomes quite clear at how efficient it is at exploiting holes in conventional programs evaluate functions, especially toward the late midgame / early endgame.

[MikeB]

I would say the result is much more dominating that the Elo difference would suggest. If one looks at the games, it becomes quite clear at how efficient it is at exploiting holes in conventional programs evaluate functions, especially toward the late midgame / early endgame.

I wrote that before going through the games and I only have gone through two of them, but as you suggest it does appear more dominating than the ELO would suggest.