Changes

an adaption of [[Gian-Carlo Pascutto|Gian-Carlo Pascutto's]] [[Leela Zero]] [[Go]] project <ref>[https://github.com/gcp/leela-zero GitHub - gcp/leela-zero: Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper]</ref> to [[Chess]], using initiated and announced by [[Stockfish|Stockfish's]] co-author [[Board Representation|board representationGary Linscott]] and , who was already responsible for the Stockfish [[Move GenerationStockfish#TestingFramework|move generationTesting Framework]]. No heuristics or prior [[Knowledge|knowledge]] are carried over from Stockfishcalled ''Fishtest''. Leela Chess is [[:Category:Open Source|open source]], released under the terms of [[Free Software Foundation#GPL|GPL version 3]] or later, and supports [[UCI]]. The goal is to build a strong [[UCT]] chess AI playing entity following the same type of [[Deep Learning|deep learning]] along with [[Monte-Carlo Tree Search|Monte-Carlo tree search]] (MCTS) techniques of [[AlphaZero]] as described in [[DeepMind|DeepMind's]] paper 2017 and 2018 papers <ref>[[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Matthew Lai]], [[Arthur Guez]], [[Marc Lanctot]], [[Laurent Sifre]], [[Dharshan Kumaran]], [[Thore Graepel]], [[Timothy Lillicrap]], [[Karen Simonyan]], [[Demis Hassabis]] ('''2017'''). ''Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm''. [https://arxiv.org/abs/1712.01815 arXiv:1712.01815]</ref><ref>[[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Matthew Lai]], [[Arthur Guez]], [[Marc Lanctot]], [[Laurent Sifre]], [[Dharshan Kumaran]], [[Thore Graepel]], [[Timothy Lillicrap]], [[Karen Simonyan]], [[Demis Hassabis]] ('''2018'''). ''[http://science.sciencemag.org/content/362/6419/1140 A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play]''. [https://en.wikipedia.org/wiki/Science_(journal) Science], Vol. 362, No. 6419</ref><ref>[http://blog.lczero.org/2018/12/alphazero-paper-and-lc0-v0191.html AlphaZero paper, and Lc0 v0.19.1] by [[Alexander Lyashuk|crem]], [[Leela Chess Zero|LCZero blog]], December 07, 2018</ref>, but using distributed training for the weights of the [[Neural Networks#Deep|deep]] [[Neural Networks#ResidualConvolutional|convolutional neural network]] (CNN, DNN, DCNN).  =Lc0=Leela Chess Zero consists of an executable to play or analyze [[Chess Game|games]], initially dubbed '''LCZero''', soon rewritten by a team around [[Alexander Lyashuk]] for better performance and then called '''Lc0''' <ref>[https://github.com/LeelaChessZero/lc0/wiki/lc0-transition lc0 transition · LeelaChessZero/lc0 Wiki · GitHub]</ref> <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=68094&start=91 Re: TCEC season 13, 2 NN engines will be participating, Leela and Deus X] by [[Gian-Carlo Pascutto]], [[CCC]], August 03, 2018</ref>. This executable, the actual chess engine, performs the [[Monte-Carlo Tree Search|residualMCTS]] and reads the self-taught [[Neural Networks#Convolutional|convolutional neural networkCNN]], which weights are persistent in a separate file.Lc0 is written in [[Cpp|C++]] (started with [[Cpp#14|C++14]] then upgraded to [[Cpp#17|C++17]]) and may be compiled for various platforms and backends. The training process requires Since deep CNN approaches are best suited to run massively in parallel on [[GPU|GPUs]] to perform all the [[Float|floating point]] [https://en.wikipedia.org/wiki/Dot_product dot products] for thousands of neurons, the preferred target platforms are [[Nvidia]] [[GPU|GPUs]] supporting [https://en.wikipedia.org/wiki/CUDA CUDA] and a [https://en.wikipedia.org/wiki/CuDNN CuDNN] libraries <ref>[https://developer.nvidia.com/cudnn NVIDIA cuDNN | NVIDIA Developer]</ref>. [[Ankan Banerjee]] wrote the CuDNN backend code, also shared by [[Deus X]] and [[Allie]] <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=71822&start=48 Re: My failed attempt to change TCEC NN clone rules] by [[Adam Treat]], [[CCC]], September 19, 2019</ref>. None CUDA compliant GPUs ([[AMD]]) are supported through [[GPUOpenCL]] accelerated version of , while much slower pure CPU binaries are possible using [https://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms BLAS], target systems with or without a [https://en.wikipedia.org/wiki/TensorFlow TensorflowVideo_card graphics card] (GPU) are [[Linux]], [[Mac OS]] and [[Windows]] computers, or BLAS only the [[Raspberry Pi]]. =Description=Like [[AlphaZero]], Lc0's [[Evaluation|evaluates]] [[Chess Position|positions]] using non-linear function approximation based on a [[Neural Networks|deep neural network]], rather than the [[Evaluation#Linear|linear function approximation]] as used in classical chess programs. This neural network takes the board position as input and outputs position evaluation (QValue) and a vector of move probabilities (PValue, policy). Once trained, these network is combined with a [[Monte-Carlo Tree Search]] (MCTS) using the policy to narrow down the search to high­probability moves, and using the value in conjunction with a fast rollout policy to evaluate positions in the tree. The MCTS selection is done by a variation of [[Christopher D. Rosin|Rosin's]] [[UCT]] improvement dubbed [[Christopher D. Rosin#PUCT|PUCT]] (Predictor + UCT). ==[[Board Representation]]==Lc0's color agnostic board is represented by five [[Bitboards|bitboards]] (own pieces, opponent pieces, orthogonal sliding pieces, diagonal sliding pieces, and pawns including [[En passant|en passant]] target information coded as pawns on rank 1 and 8), two king squares, [[Castling Rights|castling rights]], and a flag whether the board is [[Color Flipping|color flipped]]. Getting individual piece bitboards requires some [[General Setwise Operations|setwise operations]] such as [[General Setwise Operations#Intersection|intersection]] and [[General Setwise Operations#RelativeComplement|set theoretic difference]] installed <ref>[https://github.com/glinscottLeelaChessZero/leela-chesslc0/blob/master/READMEsrc/chess/board.md leela-chessh lc0/READMEboard.md h at master · glinscottLeelaChessZero/lc0 · GitHub]</ref>. ==Network==While [[AlphaGo]] used two disjoint networks for policy and value, [[AlphaZero]] as well as Leela Chess Zero, share a common "body" connected to disjoint policy and value "heads". The “body” consists of spatial 8x8 planes, using B [[Neural Networks#Residual|residual]] blocks with F filters of kernel size 3x3, stride 1. So far, model sizes FxB of 64x6, 128x10, 192x15, and 256x20 were used.  Concerning [[Nodes per Second|nodes per second]] of the MCTS, smaller models are faster to calculate than larger models. They are faster to train and will earlier recognize progress, but they will also saturate earlier so that at some point more training will no longer improve the engine. Larger and deeper network models will improve the receptivity, the amount of knowledge and pattern to extract from the training samples, with potential for a [[Playing Strength|stronger]] engine. As a further improvement, Leele Chess Zero applies the ''Squeeze and Excite'' (SE) extension to the residual block architecture <ref>[https://github.com/LeelaChessZero/lc0/leelawiki/Technical-Explanation-of-Leela-Chess-Zero Technical Explanation of Leela Chess Zero · LeelaChessZero/lc0 Wiki · GitHub]</ref> <ref>[https://towardsdatascience.com/squeeze-and-excitation-networks-9ef5e71eacd7 Squeeze-and-Excitation Networks – Towards Data Science] by [http://plpp.de/ Paul-Louis Pröve], October 17, 2017</ref>. The body is connected to both the policy "head" for the move probability distribution, and the value "head" for the evaluation score aka [[Pawn Advantage, Win Percentage, and Elo|winning probability]] of the current position and up to seven predecessor positions on the input planes. ==Training==Like in [[AlphaZero]], the '''Zero''' suffix implies no other initial knowledge than the rules of the game, to build a superhuman player, starting with truly random self-play games to apply [[Reinforcement Learning|reinforcement learning]] based on the outcome of that games. However, there are derived approaches, such as [[Albert Silver|Albert Silver's]] [[Deus X]], trying to take a short-cut by initially using [[Supervised Learning|supervised learning]] techniques, such as feeding in high quality games played by other strong chess · playing entities, or huge records of positions with a given preferred move.The unsupervised training of the NN is about to minimize the [https://en.wikipedia.org/wiki/Norm_(mathematics)#Euclidean_norm L2-norm] of the [https://en.wikipedia.org/wiki/Mean_squared_error mean squared error] loss of the value output and the policy loss. Further there are experiments to train the value head against not the game outcome, but against the accumulated value for a position after exploring some number of nodes with [[UCT]] <ref>[https://medium.com/oracledevs/lessons-from-alphazero-part-4-improving-the-training-target-6efba2e71628 Lessons From AlphaZero (part 4): Improving the Training Target] by [https://blogs.oracle.com/author/vish-abrams Vish Abrams], [https://blogs.oracle.com/ Oracle Blog], June 27, 2018</ref>. The distributed training is realized with an sophisticated [https://en.wikipedia.org/wiki/Client%E2%80%93server_model client-server model]. The client, written entirely in the [[Go (Programming Language)|Go programming language]], incorporates Lc0 to produce self-play games.Controlled by the server, the client may download the latest network, will start self-playing, and uploading games to the server, who on the other hand will regularly produce and distribute new neural network weights after a certain amount of games available from contributors. The training software consists of [[Python]] code, the pipeline requires [https://en.wikipedia.org/wiki/NumPy NumPy] and [https://en.wikipedia.org/wiki/TensorFlow TensorFlow] running on [[Linux]] <ref>[https://github.com/LeelaChessZero/lczero-training GitHub- LeelaChessZero/lczero-training: For code etc relating to the network training process.]</ref>. The server is written in [[Go (Programming Language)|Go]] along with [[Python]] and [https://en.wikipedia.org/wiki/Shell_script shell scripts]. =Structure Diagrams= [[FILE:lc0diagram.png|none|border|text-bottom]] Related to [[TCEC]] clone discussions concerning [[Deus X]] and [[Allie]] aka [[Allie#AllieStein|AllieStein]],<br/>[[Alexander Lyashuk]] published diagrams with all components of the affected engines,<br/>The above shows the common legend, and the structure of all Leela Chess Zero's components based on current Lc0 engine <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=71822 My failed attempt to change TCEC NN clone rules] by [[Alexander Lyashuk]], [[CCC]], September 14, 2019 » [[TCEC]]</ref>[[FILE:Lczero.png|none|border|text-bottom|670px]]Same diagram, but initial LCZero engine, which played [[TCEC Season 12]] <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=71822 My failed attempt to change TCEC NN clone rules] by [[Alexander Lyashuk]], [[CCC]], September 14, 2019 » [[TCEC]]</ref>

=lc0Tournament Play===First Experience==Soon after LCZero gained first tournament experience in April 2018 at [[TCEC Season 12]] and over the start board at the [[WCCC 2018]]in [https://en.wikipedia.org/wiki/Stockholm Stockholm], July 2018. It won the [[TCEC Season 13#Fourth|fourth division]] of [[TCEC Season 13]] in August 2018, [[#Lc0|Lc0]] finally coming in third in the project[[TCEC Season 13#Third|third division]].==Breakthrough==[[TCEC Season 14]] from November 2018 until February 2019 became a breakthrough, Lc0 winning the [[TCEC Season 14#Third|third]], [[TCEC Season 14#Second|second]] and [[TCEC Season 14#First|first]] division, some of to even [[TCEC Season 14#Premier|qualify]] for the team led [[TCEC Season 14#Superfinal|superfinal]], losing by the narrow margin of +10 =81 -9, '''50½ - 49½''' versus [[Alexander LyashukStockfish]] started to rewrite .Again runner-up at the engine from scratch[[TCEC Season 15#Premier|TCEC Season 15 premier division]] in April 2019,Lc0 aka '''LCZero v0.21.1-nT40.T8. The new engine dubbed 610'''lc0won the [[TCEC Season 15#Superfinal|superfinal]] in May 2019 versus Stockfish with +14 =79 -7, ''' was able to search 453½-8 times faster than lczero on 46½''' <ref>[https://enblog.wikipedialczero.org/wiki2019/05/lc0-won-tcec-15.html Lc0 won TCEC 15] by [[Alexander Lyashuk|crem]], [[Leela Chess Zero|LCZero blog]], May 28, 2019</Nvidia Nvidia ref>.At the [[TCEC Season 16#Premier|TCEC Season 16 premier division]] in September 2019, Lc0 became in third behind Stockfish and the [[Supervised Learning|supervised]] trained [[Allie#AllieStein|AllieStein]],but Lc0 took revenge by winning the [[TCEC Season 17#Premier|TCEC Season 17 premier division]] in spring 2020, as '''LCZero v0.24-sv-t60-3010''' fighting down Stockfish in a thrilling [[TCEC Season 17#Superfinal|superfinal]GPU’s ] in April 2020 with +17 =71 -12, '''52½-47½''' <ref>[https://lczero.org/blog/2020/04/tcec-s17-super-final-report/ TCEC S17 SUper FInal report] by @glbchess64, [[Leela Chess Zero|LCZero blog]], April 21, 2020</ref>, but tables turned again in [[TCEC Season 18#Premier|TCEC Season 18]], when Stockfish won the [[TCEC Season 18#Superfinal|superfinal]]. =Release Dates===2018==* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.lczero14.1 - July 08, 2018* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.16.org0 - July 20, 2018* [[Leela Chess Zero]] /[[Leela Chess Zero#Lc0|Lc0]] v0.17.0 - August 27, 2018* [[Leela Chess Zero]] /06[[Leela Chess Zero#Lc0|Lc0]] v0.18.0 - September 30, 2018* [[Leela Chess Zero]] /[[Leela Chess Zero#Lc0|Lc0]] v0.18.1 - October 02, 2018* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.19.0 - November 19, 2018* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.19.1.1 - December 10, 2018==2019==* [[Leela Chess Zero]] /[[Leela Chess Zero#Lc0|Lc0]] v0.20.9 - January 01, 2019* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.20.1 - January 07, 2019* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.20.2 - February 01, 2019* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.21.1 - March 23, 2019* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.21.2-theJune 09, 2019* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.21.4 - July 28, 2019* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.22.0 - August 05, 2019* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.23.2 - December 31, 2019==2020==* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.23.3 - February 18, 2020* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.24.1 - March 15, 2020* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.25.1 - April 30, 2020* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.26.0 - July 02, 2020* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.26.1 - July 15, 2020* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.26.2 -waySeptember 02, 2020* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] v0.26.3 -forwardOctober 10, 2020==2021==* [[Leela Chess Zero]] / The Way Forward · [[Leela Chess Zero#Lc0|Lc0]<] [https://ref>github. Training has changed to require com/LeelaChessZero/lc0 instead of lczero <ref>/releases/tag/v0.27.0 v0.27.0] - February 21, 2021* [[Leela Chess Zero]] / [[Leela Chess Zero#Lc0|Lc0]] [httphttps://lczerogithub.com/LeelaChessZero/lc0/releases/tag/v0.28.0 v0.28.org0] - August 26, 2021* [[Leela Chess Zero]] / LCZero[[Leela Chess Zero#Lc0|Lc0]]<[https://github.com/LeelaChessZero/lc0/releases/tag/ref>v0.28.2 v0.28.2] - December 13, 2021 =Authors=* [[:Category:Leela Chess Contributor|Leela Chess Contributors]]

* [[Deus X]]* [[Leela Zero]]* [[Leila]]* [[Maia Chess]]* [[Monte-Carlo Tree Search]]: [[UCT]]

* [httphttps://lczero.org/ Leela Chess Zero]* [https://lczero.org/blog/ Blog - Leela Chess Zero]* [https://groups.google.com/forum/#!forum/lczero LCZero – Forum]* [https://training.lczero.org/ Testing instance of LCZeroserver]* [https://en.wikipedia.org/wiki/Leela_Chess_Zero Leela Chess Zero from Wikipedia]* [https://en.wikipedia.org/wiki/Leela_(software) Leela (software) from Wikipedia]* [https://www.facebook.com/LeelaChessZero/ Leela Chess Zero - Facebook]* [https://twitter.com/leelachesszero Leela Chess Zero (@LeelaChessZero) | Twitter]* [https://slides.com/crem/lc0#/logo Lc0 Slides] by [[Alexander Lyashuk]]==GitHub==

* [https://github.com/LeelaChessZero/lc0 /wiki/Technical-Explanation-of-Leela-Chess-Zero Technical Explanation of Leela Chess Zero · LeelaChessZero/lc0 Wiki · GitHub - ]* [https://github.com/LeelaChessZero/lc0/graphs/contributors Contributors to LeelaChessZero/lc0· GitHub]* [https: The rewritten engine//github.com/LeelaChessZero/lc0/commit/62741d56252b23f74e8a7200a42812f27fe32b7d Use NHCW layout for fused winograd residual block (#1567) · LeelaChessZero/lc0@62741d5 · GitHub], originally for tensorflow. Now all other backends have been ported herecommit by [[Ankan Banerjee]], June 10, 2021

* [https://github.com/LeelaChessZerodkappe/lczero GitHub leela-chess-weights/wiki/Distilled- LeelaChessZeroNetworks Distilled Networks · dkappe/lczero: A leela-chess adaption of GCP's Leela Zero-weights Wiki · GitHub]==Rating Lists==* [httpshttp://groupscomputerchess.googleorg.comuk/forumccrl/#!forum404/lczero LCZero – Google Groups]* [https:cgi//blogcompare_engines.lczero.org/ cgi?family=Leela%20Chess&print=Rating+list&print=Results+table&print=LOS+table&print=Ponder+hit+table&print=Eval+difference+table&print=Comopp+gamenum+table&print=Overlap+table&print=Score+with+common+opponents Leela Chess Zero - Blog] in [[CCRL|CCRL Blitz]]* [httpshttp://wwwcomputerchess.facebookorg.comuk/LeelaChessZeroccrl/ 4040/cgi/compare_engines.cgi?family=Leela%20Chess&print=Rating+list&print=Results+table&print=LOS+table&print=Ponder+hit+table&print=Eval+difference+table&print=Comopp+gamenum+table&print=Overlap+table&print=Score+with+common+opponents Leela Chess Zero - Facebook]* in [[https:CCRL|CCRL 40//en.wikipedia.org/wiki/Leela_Chess_Zero Leela Chess Zero from Wikipedia15]]==ChessBase==

* [[:Category:Marc RibotSoft Machine|Marc Ribot'sSoft Machine]] Ceramic Dog - Lies My Body Told Me (Live on [https://en.wikipedia.org/wiki/KEXP-FM KEXPHidden_Details Hidden Details], July 20, 2016)2018, [https://en.wikipedia.org/wiki/YouTube YouTube] Video : Lineup: [https://en.wikipedia.org/wiki/Theo_Travis Theo Travis], [[:Category:Roy Babbington|Roy Babbington]], [https://en.wikipedia.org/wiki/John_Etheridge John Etheridge], [[:Category:John Marshall|John Marshall]]: {{#evu:https://www.youtube.com/watch?v=YohWv7kIp5ouGIf97m243M|alignment=left|valignment=top}}

[[Category:Marc RibotGPU]][[Category:DCNN]][[Category:MCTS]][[Category:PC]][[Category:Windows]][[Category:Linux]][[Category:Mac]][[Category:Fiction]][[Category:Given Name]][[Category:Soft Machine]][[Category:Roy Babbington]][[Category:John Marshall]]