Leela Zero

A Go program with no human provided knowledge. Using MCTS (but without Monte Carlo playouts) and a deep residual convolutional neural network stack. If you are wondering what the catch is: you still need the network weights. No network weights are in this repository. If you manage to obtain the AlphaGo Zero weights, this program will be about as strong, provided you also obtain a few Tensor Processing Units. Lacking those TPUs, I'd recommend a top of the line GPU - it's not exactly the same, but the result would still be an engine that is far stronger than the top humans. Recomputing the AlphaGo Zero weights will take about 1700 years on commodity hardware. One reason for publishing this program is that we are running a public, distributed effort to repeat the work. Working together, and especially when starting on a smaller scale, it will take less than 1700 years to get a good network (which you can feed into this program, suddenly making it strong). You need a PC with a GPU, i.e. a discrete graphics card made by NVIDIA or AMD, preferably not too old, and with the most recent drivers installed. It is possible to run the program without a GPU, but performance will be much lower. If your CPU is not very recent (Haswell or newer, Ryzen or newer), performance will be outright bad, and it's probably of no use trying to join the distributed effort. But you can still play, especially if you are patient. Head to the Github releases page at download the latest release, unzip, and launch autogtp.exe. It will connect to the server automatically and do its work in the background, uploading results after each game. You can just close the autogtp window to stop it. Follow the instructions below to compile the leelaz and autogtp binaries in the build subdirectory. Then run autogtp as explained in the contributing instructions below. Contributing will start when you run autogtp. Many cloud companies offer free trials (or paid solutions, not discussed here) that are usable for helping the leela-zero project. Download the best known network weights file from here, or, if you prefer a more human style, a (weaker) network trained from human games here. If you are on Windows, download an official release from here and head to the Usage section of this README. If you are on macOS, Leela Zero is available through Homebrew, the de facto standard package manager. You can install it with: If you are on Unix, you have to compile the program yourself. Follow the compilation instructions below and then read the Usage section. GCC, Clang or MSVC, any C++14 compiler Boost 1.58.x or later, headers and program options, filesystem and system libraries (libboost-dev, libboost-program-options-dev and libboost-filesystem-dev on Debian/Ubuntu) zlib library (zlib1g & zlib1g-dev on Debian/Ubuntu) Standard OpenCL C headers (opencl-headers on Debian/Ubuntu, or at OpenCL ICD loader (ocl-icd-libopencl1 on Debian/Ubuntu, or reference implementation at An OpenCL capable device, preferably a very, very fast GPU, with recent drivers is strongly recommended (OpenCL 1.1 support is enough). Don't forget to install the OpenCL driver if this part is packaged seperately by the Linux distribution (e.g. nvidia-opencl-icd). If you do not have a GPU, add the define "USE CPU ONLY", for example by adding -DUSE CPU ONLY=1 to the cmake command line. Optional: BLAS Library: OpenBLAS (libopenblas-dev) or Intel MKL The program has been tested on Windows, Linux and macOS. Compile leelaz and autogtp in build subdirectory with cmake cmake .. cmake --build . Compile leelaz and autogtp in build subdirectory with cmake cmake .. cmake --build . cd msvc Double-click the leela-zero2015.sln or leela-zero2017.sln corresponding to the Visual Studio version you have. Build from Visual Studio 2015 or 2017 For Windows, you can use a release package, see "I want to help". Leela Zero is not meant to be used directly. You need a graphical interface for it, which will interface with Leela