minigrid.farama.org Open in urlscan Pro
2606:50c0:8002::153  Public Scan

Form analysis
1 forms found in the DOM

GET search/

<form class="sidebar-search-container" method="get" action="search/" role="search">
  <input class="sidebar-search" placeholder="Search" name="q" aria-label="Search">
  <input type="hidden" name="check_keywords" value="yes">
  <input type="hidden" name="area" value="default">
</form>

Text Content

Toggle site navigation sidebar
MiniGrid Documentation
Farama Foundation

Core Projects
 * Gymnasium
 * PettingZoo
 * Minari

Mature Projects
Documentation
 * Minigrid
 * Gymnasium-Robotics
 * MAgent2
 * Miniworld
 * MiniWoB++
 * Shimmy
 * MO-Gymnasium

Repositories
 * SuperSuit
 * Tinyscaler
 * AutoROM
 * Jumpy

Incubating Projects
Documentation
 * ViZDoom
 * HighwayEnv

Repositories
 * Arcade Learning Environment
 * D4RL
 * MicroRTS
 * Procgen2
 * Metaworld
 * CrowdPlay
 * Stable-Retro
 * ChatArena

Foundation
 * About
 * Standards
 * Donate

Contents Menu Expand Light mode Dark mode Auto light/dark mode
Hide navigation sidebar
Hide table of contents sidebar
MiniGrid Documentation



Introduction

 * Basic Usage
 * Training an Agent
 * List of Publications
 * Tutorial on Creating Environments
 * Training Minigrid Environments
 * Create Custom Feature Extractor
 * Train a PPO Agent
 * Further Reading

Wrappers

 * Wrapper
   Toggle navigation of Wrapper
   * Action Bonus
   * Dict Observation Space
   * Direction Obs
   * FlatObs
   * Fully Obs
   * No Death
   * Observation
   * One Hot Partial Obs
   * Reseed
   * RGB Img Obs
   * Position Bonus
   * Symbolic Obs
   * View Size

Environments

 * Minigrid Environments
   Toggle navigation of Minigrid Environments
   * Blocked Unlock Pickup
   * Crossing
   * Dist Shift
   * Door Key
   * Dynamic Obstacles
   * Empty
   * Fetch
   * Four Rooms
   * Go To Door
   * Go To Object
   * Key Corridor
   * Lava Gap
   * Locked Room
   * Memory
   * Multi Room
   * Obstructed Maze Dlhb
   * Obstructed Maze Full
   * Playground
   * Put Near
   * Red Blue Door
   * Unlock
   * Unlock Pickup
 * BabyAI Environments
   Toggle navigation of BabyAI Environments
   * Go To Red Ball Grey
   * Go To Red Ball
   * Go To Red Ball No Dists
   * Go To Obj
   * Go To Local
   * Go To
   * Go To Imp Unlock
   * Go To Seq
   * Go To Red Blue Ball
   * Go To Door
   * Go To Obj Door
   * Open
   * Open Red Door
   * Open Door
   * Open Two Doors
   * Open Doors Order
   * Pickup
   * Unblock Pickup
   * Pickup Loc
   * Pickup Dist
   * Pickup Above
   * Put Next Local
   * Put Next
   * Unlock
   * Unlock Local
   * Key In Box
   * Unlock Pickup
   * Blocked Unlock Pickup
   * Unlock To Unlock
   * Action Obj Door
   * Find Obj
   * Key Corridor
   * One Room
   * Move Two Across
   * Synth
   * Synth Loc
   * Synth Seq
   * Mini Boss Level
   * Boss Level
   * Boss Level No Unlock

Development

 * Release Notes
 * Github

Back to top
Edit this page
Toggle Light / Dark / Auto color theme
Toggle table of contents sidebar


MINIGRID CONTAINS SIMPLE AND EASILY CONFIGURABLE GRID WORLD ENVIRONMENTS TO
CONDUCT REINFORCEMENT LEARNING RESEARCH. THIS LIBRARY WAS PREVIOUSLY KNOWN AS
GYM-MINIGRID.

This library contains a collection of 2D grid-world environments with
goal-oriented tasks. The agent in these environments is a triangle-like agent
with a discrete action space. The tasks involve solving different maze maps and
interacting with different objects such as doors, keys, or boxes. The design of
the library is meant to be simple, fast, and easily customizable.

In addition, the environments found in the BabyAI repository have been included
in Minigrid and will be further maintained under this library.

The Gymnasium interface allows to initialize and interact with the Minigrid
default environments as follows:

import gymnasium as gym
env = gym.make("MiniGrid-Empty-5x5-v0", render_mode="human")
observation, info = env.reset(seed=42)
for _ in range(1000):
   action = policy(observation)  # User-defined policy function
   observation, reward, terminated, truncated, info = env.step(action)

   if terminated or truncated:
      observation, info = env.reset()
env.close()


To cite this project please use:

@article{MinigridMiniworld23,
  author       = {Maxime Chevalier-Boisvert and Bolun Dai and Mark Towers and Rodrigo de Lazcano and Lucas Willems and Salem Lahlou and Suman Pal and Pablo Samuel Castro and Jordan Terry},
  title        = {Minigrid \& Miniworld: Modular \& Customizable Reinforcement Learning Environments for Goal-Oriented Tasks},
  journal      = {CoRR},
  volume       = {abs/2306.13831},
  year         = {2023},
}






Copyright © 2023 Farama Foundation



This page uses Google Analytics to collect statistics.

DenyAllow
v2.3.1 (latest)
Versions
   
 * main (unstable)
 * v2.3.1 (latest)
 * v2.3.0
 * v2.2.1
 * v2.2.0