Tensors and Dynamic neural networks in Python with strong GPU acceleration

Eclipse SUMO is an open source, highly portable, microscopic and continuous traffic simulation package designed to handle large networks. It allows for intermodal simulation including pedestrians a…

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

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

Train transformer language models with reinforcement learning.

Manipulation and analysis of geometric objects

Massively parallel rigidbody physics simulation on accelerator hardware.

Optional static typing for Python

C++ Library Manager for Windows, Linux, and MacOS

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Optax is a gradient processing and optimization library for JAX.

A markdown version emoji cheat sheet

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Flax is a neural network library for JAX that is designed for flexibility.

🕹️ A diverse suite of scalable reinforcement learning environments in JAX

🚀 Efficient implementations of state-of-the-art linear attention models

☄🌌️ The minimal, blazing-fast, and infinitely customizable prompt for any shell!

A computer algebra system written in pure Python

Open MPI main development repository

Multi-Agent Reinforcement Learning with JAX

Bring background images to your vscode. vscode background 背景扩展插件。

[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

A Survey of Reinforcement Learning for Large Reasoning Models

📚 Freely available programming books

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Code for "SimbaV2: Hyperspherical Normalization for Scalable Deep Reinforcement Learning"