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>. 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#14|C++14]] and may be compiled for various platforms and backends. Since deep CNN approaches are best suited to run massively in parallel on [[GPU|GPUs]] to perform all the [[Float|floating point]][https://en. The training process requires wikipedia.org/wiki/Dot_product dot products] for thousands of neurons, the preferred target platforms are [[Nvidia]] [[GPU|GPU’s]] supporting [https://en.wikipedia.org/wiki/CUDA CUDA] and a cuDNN libraries <ref>[https://developer.nvidia.com/cudnn NVIDIA cuDNN | NVIDIA Developer]</ref>.None CUDA compliant GPUs ([[GPUAMD]] accelerated version of ) are supported through [https://en.wikipedia.org/wiki/OpenCL OpenCL], 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, casting rights, and a flag whether the board is [[Color Flipping|color flipped]].While the structure is suitable as input for the neural network, getting individual pieces 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 input planes, followed by convolutional layers with B [[Neural Networks#Residual|residual]] blocks times 3x3xF filters. BxF specifies the model and size of the CNN (64x6, 128x10, 192x15, 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 one may 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:/leela/github.com/LeelaChessZero/lc0/wiki/Technical-Explanation-of-Leela-Chess-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 fully connected to both the policy "head" for the move probability distribution, and value "head" for the evaluation score aka [[Pawn Advantage, Win Percentage, and Elo|winning probability]] of the the the current positions 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 games, 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>.

=lc0=The distributed training is realized with an sophisticated [https://en.wikipedia.org/wiki/Client%E2%80%93server_model client-server model]. Soon after the start of the projectThe client, some of written entirely in the team led by [[Alexander LyashukGo (Programming Language)|Go programming language]] started , incorporates Lc0 to rewrite produce self-play games.Controlled by the engine 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 scratchcontributors. The new engine dubbed '''lc0''' was able to search 4-8 times faster than lczero on training software consists of [[Python]] code, the pipeline requires [https://en.wikipedia.org/wiki/Nvidia Nvidia NumPy NumPy]GPU’s <ref>and [https://blogen.lczerowikipedia.org/2018wiki/06TensorFlow TensorFlow] running on [[Linux]] <ref>[https:/18/2github.com/LeelaChessZero/lczero-thetraining GitHub -wayLeelaChessZero/lczero-forward/ The Way Forward · Leela Chess Zerotraining: For code etc relating to the network training process.]</ref>. Training has changed to require lc0 instead of lczero <ref>The server is written in [[Go (Programming Language)|Go]] along with [[Python]] and [httphttps://lczeroen.wikipedia.org/ LCZerowiki/Shell_script shell scripts]</ref>.

* [[Monte-Carlo Tree Search]]: [[UCT]]

* [https://medium.com/oracledevs/lessons-from-implementing-alphazero-7e36e9054191 Lessons From Implementing AlphaZero] by [https://medium.com/@akprasad Aditya Prasad], [https://blogs.oracle.com/ Oracle Blog], June 05, 2018: [https://medium.com/oracledevs/lessons-from-alphazero-connect-four-e4a0ae82af68 Lessons from AlphaZero: Connect Four] by [https://medium.com/@akprasad Aditya Prasad], [https://blogs.oracle.com/ Oracle Blog], June 13, 2018: [https://medium.com/oracledevs/lessons-from-alphazero-part-3-parameter-tweaking-4dceb78ed1e5 Lessons from AlphaZero (part 3): Parameter Tweaking] by [https://medium.com/@akprasad Aditya Prasad], [https://blogs.oracle.com/ Oracle Blog], June 20, 2018: [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: [https://medium.com/oracledevs/lessons-from-alpha-zero-part-5-performance-optimization-664b38dc509e Lessons From Alpha Zero (part 5): Performance Optimization] by [https://blogs.oracle.com/author/anthony-young Anthony Young], [https://blogs.oracle.com/ Oracle Blog], July 03, 2018: [https://medium.com/oracledevs/lessons-from-alpha-zero-part-6-hyperparameter-tuning-b1cfcbe4ca9a Lessons From Alpha Zero (part 6) — Hyperparameter Tuning] by [https://blogs.oracle.com/author/anthony-young Anthony Young], [https://blogs.oracle.com/ Oracle Blog], July 11, 2018* [http://blog.lczero.org/ 2018/10/understanding-training-against-q-as.html Understanding Training against Q as Knowledge Distillation] by Cyanogenoid, [[Leela Chess Zero - Blog|LCZero blog]],

* [https://github.com/LeelaChessZero/lc0 GitHub /wiki/Technical-Explanation-of-Leela-Chess- Zero Technical Explanation of Leela Chess Zero · LeelaChessZero/lc0: The rewritten engine, originally for tensorflow. Now all other backends have been ported hereWiki · GitHub]

* [https://githubblog.com/LeelaChessZero/lczero GitHub - LeelaChessZero.org/lczero: A chess adaption of GCP's Leela Chess Zero- Blog]

* [https://entwitter.wikipedia.org/wikicom/Leela_Chess_Zero leelachesszero Leela Chess Zero from Wikipedia(@LeelaChessZero) | Twitter]