flatland-association/flatland-rl

[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.

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

A construction kit for reinforcement learning environment management.

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

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Distributed Reinforcement Learning accelerated by Lightning Fabric

Simple and easily configurable grid world environments for reinforcement learning

A toolkit for developing and comparing reinforcement learning algorithms.

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