search

crowdAI / marLo

Multi Agent Reinforcement Learning using MalmÖ
MIT License
244 stars 46 forks source link

readme

.. image:: https://raw.githubusercontent.com/crowdAI/crowdai/master/app/assets/images/misc/crowdai-logo-smile.svg?sanitize=true :align: center

MarLÖ : Reinforcement Learning + Minecraft = Awesomeness

.. image:: https://readthedocs.org/projects/marlo/badge/

YOU-NEED-TO-READ-THIS : We are actively looking for maintainers for this library. If you are interested in helping maintain this library, please drop in a line here :smile:

MarLÖ (short for Multi-Agent Reinforcement Learning in MalmÖ) is a high level API built on top of Project MalmÖ <https://github.com/Microsoft/malmo> to facilitate Reinforcement Learning experiments with a great degree of generalizability, capable of solving problems in pseudo-random, procedurally changing single and multi agent environments withing the world of the mediatic phenomenon game Minecraft <https://en.wikipedia.org/wiki/Minecraft> .

The Malmo platform <https://github.com/Microsoft/malmo>_ provides an API which enables access to actions, observations (i.e. location, surroundings, video frames, game statistics) and other general data that Minecraft provides. Marlo, on the other hand, is a wrapper for Malmo that provides a higher level API and more standardized RL-friendly environment for scientific study.

The framework is written as an extension to OpenAI's Gym framework <https://github.com/openai/gym>_ , which is a toolkit for developing and comparing reinforcement learning algorithms, thus providing an industry-standard and familiar platform for scientists, developers and popular RL frameworks.

The framework was used in the 2018 MarLo Challenge <https://www.crowdai.org/challenges/marlo-2018>_.

.. list-table:: :header-rows: 0 :widths: 2 2 2 :align: center

Please consider citing the following paper if you find this work useful :

Diego Perez-Liebana, Katja Hofmann, Sharada Prasanna Mohanty, Noburu Kuno, Andre Kramer, Sam Devlin, Raluca D. Gaina “The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition”, 2019, Challenges in Machine Learning (NIPS Workshop), 2018; _<http://arxiv.org/abs/1901.08129>.

Contents

Simple Example

.. code-block:: python

!/usr/bin/env python

Please ensure that you have a Minecraft client running on port 10000

by doing :

$MALMO_MINECRAFT_ROOT/launchClient.sh -port 10000

import marlo client_pool = [('127.0.0.1', 10000)] join_tokens = marlo.make('MarLo-FindTheGoal-v0', params={ "client_pool": client_pool })

As this is a single agent scenario,

there will just be a single token

assert len(join_tokens) == 1 join_token = join_tokens[0]

env = marlo.init(join_token)

observation = env.reset()

done = False while not done: _action = env.action_space.sample() obs, reward, done, info = env.step(_action) print("reward:", reward) print("done:", done) print("info", info) env.close()

Authors