Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

A hyperparameter optimization framework

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

🔎 📈 🐍 💰 Backtest trading strategies in Python.

Deep Learning and Reinforcement Learning Library for Scientists and Engineers

Unified framework for robot learning built on NVIDIA Isaac Sim

A PyTorch native platform for training generative AI models

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Massively Parallel Deep Reinforcement Learning. 🔥

A high-performance distributed training framework for Reinforcement Learning

Robotics Toolbox for Python

PyRobot: An Open Source Robotics Research Platform

FinRL­®-Meta: Dynamic datasets and market environments for FinRL.

Deep Neuroevolution

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

3D visualization of scientific data in Python

Time series distances: Dynamic Time Warping (fast DTW implementation in C)

pyclustering is a Python, C++ data mining library.

Scalable Multi-Agent RL Training School for Autonomous Driving

Reinforcement Learning Environments for Omniverse Isaac Gym

This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym

A Configurable Recommender Systems Simulation Platform

A PyTorch Platform for Distributed RL

Reinforcement Learning for Solving the Vehicle Routing Problem

Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/

Cloud-native Financial Reinforcement Learning

Coder for "On the Continuity of Rotation Representations"

Bimanual Dexterous Teleoperation with Real-Time Retargeting using VisionPro