Marl Python Packages

torchrl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

torchrl-nightly

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

vmas

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

multi-agent-rlenv

Strongly typed reinforcement learning environment framework

jaxmarl

Multi-Agent Reinforcement Learning with JAX

pogema

[ICLR-2025] POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environment that was specifically designed to be flexible, tunable and scalable. It can be tailored to a variety of PO-MAPF / MAPF settings.

benchmarl

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

urbanmarl

Vectorized urban multi-agent reinforcement learning for 6G geospatial and radio digital twins.

marl-battlegrounds

The JAX-native Benchmark for Heterogeneous and Competitive Multi-agent Reinforcement Learning: built from scratch by researchers, for researchers.

alem-env

Can LLM/MARL agents coordinate in long-horizon, open-ended tasks? NeurIPS 2026 (Evaluations and Datasets).

sorrel

A Python interface for simple and flexible MARL environments.

pymarlzooplus

An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks

xdrl

🔬 Explainability for deep RL.

ride-gym

Official Repository for The Paper, RideGym: A Standardized Interface for Real-World Large-Scale Ride-Sharing System

marl

Multi-agent reinforcement learning framework