Metadata-Version: 2.2
Name: miniworld
Version: 2.1.0
Summary: Minimalistic 3D interior environment simulator for reinforcement learning & robotics research.
Home-page: https://github.com/Farama-Foundation/Miniworld
Author: Farama Foundation
Author-email: contact@farama.org
License: Apache
Keywords: Environment,Agent,RL,Gym,Robotics,3D
Classifier: Development Status :: 5 - Production/Stable
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: numpy>=1.22.0
Requires-Dist: pyglet<2.0,>=1.5.27
Requires-Dist: gymnasium>=0.29.1
Provides-Extra: testing
Requires-Dist: pytest>=7.0.1; extra == "testing"
Requires-Dist: torch; extra == "testing"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

<p align="center">
    <img src="https://raw.githubusercontent.com/Farama-Foundation/Miniworld/master/miniworld-text.png" width="500px"/>
</p>

Miniworld is being maintained by the Farama Foundation (https://farama.org/project_standards). See the [Project Roadmap](https://github.com/Farama-Foundation/Miniworld/issues/103) for details regarding the long-term plans.

[![Build Status](https://travis-ci.org/maximecb/gym-miniworld.svg?branch=master)](https://travis-ci.org/maximecb/gym-miniworld)

Contents:
- [Introduction](#introduction)
- [Installation](#installation)
- [Usage](#usage)
- [Environments](https://miniworld.farama.org/content/env_list/)
- [Design and Customization](https://miniworld.farama.org/content/design/)
- [Troubleshooting](https://miniworld.farama.org/content/troubleshooting/)

## Introduction

MiniWorld is a minimalistic 3D interior environment simulator for reinforcement
learning &amp; robotics research. It can be used to simulate environments with
rooms, doors, hallways and various objects (eg: office and home environments, mazes).
MiniWorld can be seen as a simpler alternative to VizDoom or DMLab. It is written
100% in Python and designed to be easily modified or extended by students.

<p align="center">
    <img src="images/maze_top_view.jpg" width=260 alt="Figure of Maze environment from top view">
    <img src="images/sidewalk_0.jpg" width=260 alt="Figure of Sidewalk environment">
    <img src="images/collecthealth_0.jpg" width=260 alt="Figure of Collect Health environment">
</p>

Features:
- Few dependencies, less likely to break, easy to install
- Easy to create your own levels, or modify existing ones
- Good performance, high frame rate, support for multiple processes
- Lightweight, small download, low memory requirements
- Provided under a permissive MIT license
- Comes with a variety of free 3D models and textures
- Fully observable [top-down/overhead view](images/maze_top_view.jpg) available
- [Domain randomization](https://blog.openai.com/generalizing-from-simulation/) support, for sim-to-real transfer
- Ability to [display alphanumeric strings](images/textframe.jpg) on walls
- Ability to produce depth maps matching camera images (RGB-D)

Limitations:
- Graphics are basic, nowhere near photorealism
- Physics are very basic, not sufficient for robot arms or manipulation

List of publications & submissions using MiniWorld (please open a pull request to add missing entries):
- [Towards real-world navigation with deep differentiable planners](https://arxiv.org/abs/2108.05713) (VGG, Oxford, CVPR 2022)
- [Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices](https://arxiv.org/abs/2008.02790) (Stanford University, ICML 2021)
- [Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments](https://openreview.net/forum?id=MtEE0CktZht) (Texas A&M University, Kuai Inc., ICLR 2021)
- [DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs](https://arxiv.org/abs/2010.08891) (NeurIPS Offline RL Workshop, Oct 2020)
- [Pre-trained Word Embeddings for Goal-conditional Transfer Learning in Reinforcement Learning](https://arxiv.org/abs/2007.05196) (University of Antwerp, Jul 2020, ICML 2020 LaReL Workshop)
- [Temporal Abstraction with Interest Functions](https://arxiv.org/abs/2001.00271) (Mila, Feb 2020, AAAI 2020)
- [Addressing Sample Complexity in Visual Tasks Using Hindsight Experience Replay and Hallucinatory GANs](https://openreview.net/forum?id=H1xSXdV0i4) (Offworld Inc, Georgia Tech, UC Berkeley, ICML 2019 Workshop RL4RealLife)
- [Avoidance Learning Using Observational Reinforcement Learning](https://arxiv.org/abs/1909.11228) (Mila, McGill, Sept 2019)
- [Visual Hindsight Experience Replay](https://arxiv.org/pdf/1901.11529.pdf) (Georgia Tech, UC Berkeley, Jan 2019)

This simulator was created as part of work done at [Mila](https://mila.quebec/).

