Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper.

cuML - RAPIDS Machine Learning Library

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

GTP engine and self-play learning in Go

An open-source implementation of the AlphaGoZero algorithm

ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

Code for the paper "Quantifying Transfer in Reinforcement Learning"

SAI: a fork of Leela Zero with variable komi.

[CVPR'19 Best Paper Finalist] Extracting 3D human motion and contact forces from a single video