Download
Minigrid is a lightweight, minimalistic grid-world environment library for reinforcement learning (RL) research. It provides a suite of simple 2D grid-based tasks (e.g., navigating mazes, unlocking doors, carrying keys) where an agent moves in discrete steps and interacts with objects. The design emphasizes speed (agents can run thousands of steps per second), low dependency overhead, and high customizability — making it easy to define new maps, new tasks, or wrappers. It supports the Gymnasium-style environment API so that RL researchers can plug it into their existing frameworks and algorithms with minimal adaptation. Because of its simplicity, it is often used for rapid prototyping, analytic experiments, curriculum learning, or pedagogical tutorials. While it is not a full 3D simulation environment, its strength lies in enabling many environment resets and steps cheaply, which is valuable for algorithmic RL research rather than high-fidelity rendering.
Features
- Suite of configurable 2D grid-world tasks built for reinforcement learning
- Gymnasium-compatible API so existing RL toolchains integrate easily
- Extremely lightweight and fast environment implementation (few dependencies)
- Ability to customize map layouts, object types, goals and reward structures
- Designed for research, prototyping, curriculum learning and teaching
- Active community, documentation and compatibility upgrades (e.g., Gymnasium 1.0)
Project Samples
