Budapest Gambit Chess Opening: TCEC : Leela Chess with 2 Graphics Cards vs Stockfish 9 on 43 cores – Budapest Video



published: 2018-07-13 19:30:00

♚Support the channel by donating via Paypal: https://goo.gl/7HJcDq
♚Play at: https://www.chessworld.net/chessclubs/asplogin.asp?from=1053

Game quality tags: amazing, awesome, astonishing, brilliant, classic, crushing, dynamic, elegant, exceptional, excellent, exciting, fabulous, famous, fantastic, finest, flashy, greatest, important, impressive, incredible, instructive, incredible, interesting, magnificent, marvellous, memorable, mind-blowing, must see, outrageous, remarkable, scintillating, sparkling, stunning, superb, thrilling, top, unbelievable, wonderful

Info about Leela Zero:
https://en.wikipedia.org/wiki/Leela_Zero

Leela Zero is a free and open-source computer Go software released on 25 October 2017. It is developed by Belgian programmer Gian-Carlo Pascutto,[1][2][3] the author of chess engine Sjeng and Go engine Leela.[4][5]

Leela Zero’s algorithm is based on DeepMind’s 2017 paper about AlphaGo Zero.[3][6] Unlike the original Leela, which has a lot of human knowledge and heuristics programmed into it, Leela Zero only knows the basic rules and nothing more.[7]

Leela Zero is trained by a distributed effort, which is coordinated at the Leela Zero website. Members of the community provide computing resources by running the client, which generates self-play games and submits them to the server. The self-play games are used to train newer networks. Generally, over 500 clients have connected to the server to contribute resources.[7] The community has provided high quality code contributions as well.[7]

Leela Zero finished third at the BerryGenomics Cup World AI Go Tournament in Fuzhou, Fujian, China on 28 April 2018.[8]

Additionally, in early 2018 the same team branched Leela Chess Zero from the same code base, also to verify the methods in the AlphaZero paper as applied to the game of chess. AlphaZero’s use of Google TPUs was replaced by a crowd-sourcing infrastructure and the ability to use graphics card GPUs via the OpenCL library. Even so, it is expected to take a year of crowd-sourced training to make up for the dozen hours that AlphaZero was allowed to train for its chess match in the paper.[9]

Info about Alphazero:
https://en.wikipedia.org/wiki/AlphaZero

AlphaZero is a computer program developed by the Alphabet-owned AI research company DeepMind, which uses an approach similar to AlphaGo Zero’s to master not just Go, but also chess and shogi. On December 5, 2017 the DeepMind team released a preprint introducing AlphaZero, which, within 24 hours, achieved a superhuman level of play in these three games by defeating world-champion programs, Stockfish, elmo, and the 3-day version of AlphaGo Zero, in each case making use of custom tensor processing units (TPUs) that the Google programs were optimized to make use of.[1] AlphaZero was trained solely via “self-play” using 5,000 first-generation TPUs to generate the games and 64 second-generation TPUs to train the neural networks, all in parallel, with no access to opening books or endgame tables. After just four hours of training, DeepMind estimated AlphaZero was playing at a higher Elo rating than Stockfish; after 9 hours of training, the algorithm decisively defeated Stockfish 8 in a time-controlled 100-game tournament (28 wins, 0 losses, and 72 draws).[1][2][3] The trained algorithm played on a single machine with four TPUs.


Relation to AlphaGo Zero
Further information: AlphaGo Zero
AlphaZero (AZ) is a more generalized variant of the AlphaGo Zero (AGZ) algorithm, and is able to play shogi and chess as well as Go. Differences between AZ and AGZ include:[1]

AZ has hard-coded rules for setting search hyperparameters.
The neural network is now updated continually.
Go (unlike Chess) is symmetric under certain reflections and rotations; AlphaGo Zero was programmed to take advantage of these symmetries. AlphaZero is not.
Chess can end in a draw unlike Go; therefore AlphaZero can take into account the possibility of a drawn game.
AlphaZero vs. Stockfish and elmo

►Kingscrusher chess resources: http://www.chessworld.net/chessclubs/learn_coaching_chessable.asp
►Kingscrusher’s “Crushing the King” video course with GM Igor Smirnov: http://chess-teacher.com/affiliates/idevaffiliate.php?id=1933&url=2396
►FREE online turn-style chess at http://www.chessworld.net/chessclubs/asplogin.asp?from=1053
http://goo.gl/7HJcDq
►Kingscrusher resources: http://www.chessworld.net/chessclubs/learn_coaching_chessable.asp
►Playlists: http://goo.gl/FxpqEH
►Follow me at Google+ : http://www.google.com/+kingscrusher ►Play and follow broadcasts at Chess24: https://chess24.com/premium?ref=kingscrusher

Watch the original Budapest Video here

Some local news is curated - Original might have been posted at a different date/ time! Click the source link for details.

4 Comments - Write a Comment

  1. leela to overtake alphazero???

    Reply
  2. @kingscrusher

    The first 3 moves, up through black's Ng4, were pre-ordained from the opening book. The first move decided by an engine was 4. Bf4.

    After Leela failed to hold the draw as black, the score of the match after this opening was 11-4 in favor of Stockfish.

    Although Leela failed to hold, there is evidence that this win was not due to opening imbalance: Komodo failed to beat Stockfish as white in this opening in the TCEC S12 super final (they drew, while Stockfish beat Komodo as white then as it did Leela in the game after this), and also in this game Stockfish had a 0.00 eval for many consecutive midgame moves before thinking it might be losing.

    Reply
  3. You're on a roll these videos are awesome. However Alpha zero is still the uncrushable King.

    Reply

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.