How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
Minigo 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
Leela Chess Zero is a deep learning game AI and neural network chess engine that uses search algorithms to determine optimal moves and evaluate game states. It functions as a UCI chess engine, implementing the Universal Chess Interface standard for compatibility with various graphical user interfaces. The system acts as a hardware-accelerated move calculator, leveraging GPU and CPU backends to accelerate neural network inference. It supports the generation and submission of self-play games to training clients to improve the strength of its neural network models. The engine provides capabilit
NetHack is a roguelike dungeon crawler and ASCII-based role playing game. It is a turn-based adventure game featuring permanent character death and the exploration of randomly generated dungeons. The project serves as a cross-platform game engine designed to be compiled and run across diverse operating systems and hardware architectures. It focuses on retro game preservation by maintaining classic game logic for modern computing environments. The codebase implements procedural content generation for maps and encounters and utilizes a grid-based coordinate system for spatial tracking. Renderi
Stockfish is a high-performance chess engine designed to evaluate board positions and calculate optimal moves. It functions as a command-line tool that utilizes neural network-based search algorithms to assess complex game states and determine strategic advantages. The engine is fully compliant with the Universal Chess Interface, allowing it to exchange commands and move data with external graphical user interfaces and professional analysis software. The engine distinguishes itself through advanced computational strategies that maximize hardware efficiency and search depth. It employs multi-t
chess.js is a headless chess game logic engine and move validation library. It functions as a board state manager that enforces official rules, generates legal moves, and tracks game state without a user interface.
The main features of jhlywa/chess.js are: Chess Board State Managers, Chess Game Engines, Stalemate Detectors, Threefold Repetition Detectors, ASCII Board Renderers, Board State Queries, Board State Manipulators, Board Reset Utilities.
Projects with overlapping indexed features include: tensorflow/minigo — Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a… leelachesszero/lc0 — Leela Chess Zero is a deep learning game AI and neural network chess engine that uses search algorithms to determine… nethack/nethack — NetHack is a roguelike dungeon crawler and ASCII-based role playing game. It is a turn-based adventure game featuring… official-stockfish/stockfish — Stockfish is a high-performance chess engine designed to evaluate board positions and calculate optimal moves. It…