Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.

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

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

An End-To-End, Lightweight and Flexible Platform for Game Research

Reinforcement Learning environments based on the 1993 game Doom

Connecting Torch to StarCraft

A plugin for GTAV that transforms it into a vision-based self-driving car research environment.

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.

AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。

Hearthstone simulator using C++ with some reinforcement learning

A C++ framework for MDPs and POMDPs with Python bindings

ns3-gym - The Playground for Reinforcement Learning in Networking Research

PyTorch C++ Reinforcement Learning

AI Research Platform for Reinforcement Learning from Real Panoramic Images.

An open-source 3D-printed quadrupedal robot. Intuitive gait generation through 12-DOF Bezier Curves. Full 6-axis body pose manipulation. Custom 3DOF Leg Inverse Kinematics Model accounting for offsets.

Open-Source Framework for Development, Simulation and Benchmarking of Behavior Planning Algorithms for Autonomous Driving

The Fastest Deep Reinforcement Learning Library

Framework for developing OpenAI Gym robotics environments simulated with Ignition Gazebo