Go (board game) engine and AI
For limbaj de programare pentru software scalabil, the strongest matches are leela-zero/leela-zero (Leela Zero is a deep-learning Go engine that implements), tensorflow/minigo (Minigo is a TensorFlow-based Go AI engine that uses) and lightvector/katago (KataGo is a leading open-source Go AI engine that). Each is ranked by relevance to your query, popularity and recent activity.
Selectăm repository-uri open-source de pe GitHub care se potrivesc cu „go”. Rezultatele sunt clasificate după relevanța față de căutarea ta — folosește filtrele de mai jos pentru a rafina rezultatele sau utilizează AI-ul.
Rezultate pentru „limbaj de programare pentru software scalabil”
Găsește cele mai bune repo-uri cu AI.Vom căuta cele mai potrivite repository-uri folosind AI.
- leela-zero/leela-zero
leela-zero/leela-zero
5,579Vezi pe GitHubLeela Zero is a deep learning Go engine and reinforcement learning system that implements the AlphaGo Zero approach. It utilizes deep residual convolutional networks and Monte Carlo Tree Search to determine optimal moves and analyze the game of Go. The project functions as a neural network training tool that generates data through automated self-play. It uses a supervised learning pipeline to refine network weights, allowing the system to improve its game-playing capabilities without relying on human-provided data or expert knowledge. The engine includes game scoring logic to determine winne
Leela Zero is a deep-learning Go engine that implements the AlphaGo Zero approach with Monte Carlo tree search, supports GTP protocol, includes scoring logic, and handles multiple board sizes—exactly the kind of AI-driven Go implementation with game record capabilities you are looking for.
C++Monte Carlo Tree Search - tensorflow/minigo
tensorflow/minigo
3,531Vezi pe GitHubMinigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge
Minigo is a TensorFlow-based Go AI engine that uses Monte Carlo Tree Search and neural networks, and its tags indicate support for GTP protocol, SGF record parsing, and game analysis — exactly the kind of open-source Go implementation with AI you are looking for, covering the key features like MCTS, SGF, and GTP.
C++Go Text Protocol ImplementationsMonte Carlo Tree SearchMCTS Parallelization Strategies - lightvector/katago
lightvector/KataGo
Overview Training History and Research Where To Download Stuff Setting Up and Running KataGo GUIs Windows and Linux MacOS OpenCL vs CUDA vs TensorRT vs Eigen How To Use Tuning for Performance Common Questions and Issues Issues with specific GPUs or GPU drivers Common Problems Other Questions…
KataGo is a leading open-source Go AI engine that uses Monte Carlo tree search and neural networks, fully supporting SGF, GTP protocol, multiple board sizes including 9×9 and 19×19, scoring with komi, handicap stones, and can be used via command line or graphical interfaces through GTP — exactly what this search asks for.
Algorithms and Data Structures
