A Lightweight LLM Post-Training Library

Fault-tolerant async actors for Rust that scale seamlessly

Partially Observable Process Gym

Rust actor framework

Haskell's IO simulator which closely follows core packages (base, async, stm).

Data interchange with algebraic data types.

A collection of wrappers for Gymnasium and PettingZoo environments (being merged into gymnasium.wrappers and pettingzoo.wrappers

PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.

Async RL Training at Scale

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

A suite of test scenarios for multi-agent reinforcement learning.

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

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

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …

MAGE - Memgraph Advanced Graph Extensions 🔮

dynnode2vec is a python package that implements algorithms to embed dynamic graphs

A high-performance distributed training framework for Reinforcement Learning

This is Python source code for the multi-node2vec algorithm for fast embedding of multilayer networks

Graph Neural Network Library for PyTorch

Stanford Network Analysis Platform (SNAP) is a general purpose network analysis and graph mining library.

Code for our paper "Generative Flow Networks for Discrete Probabilistic Modeling"

This repository provides a reference implementation of struc2vec.

Python wrapper for TA-Lib (http://ta-lib.org/).

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

Highly-available Distributed Fault-tolerant Runtime

CuLE: A CUDA port of the Atari Learning Environment (ALE)

🍇 A C++ library for parallel graph processing (GRAPE) 🍇