Skip to content
master
Go to file
Code
This branch is 2 commits ahead, 1 commit behind semitable:master.

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 

README.md

Multi-Robot Warehouse Environment (RWARE)

A multi-agent environment for Reinforcement Learning

Installation

git clone https://github.com/semitable/robotic-warehouse.git
cd robotic-warehouse
pip install -e .

Usage

To use in Python, import it and use it as a gym environment:

import robotic_warehouse
import gym

env = gym.make("rware-tiny-2ag-v1")
n_obs = env.reset()
n_obs, n_reward, n_done, info = env.step(n_action)

where n_* is a list of length len(agents)

Citation

  1. A comperative evaluation of MARL algorithms that includes this environment
@article{papoudakis2020comparative,
  title={Comparative Evaluation of Multi-Agent Deep Reinforcement Learning Algorithms},
  author={Papoudakis, Georgios and Christianos, Filippos and Sch{\"a}fer, Lukas and Albrecht, Stefano V},
  journal={arXiv preprint arXiv:2006.07869},
  year={2020}
}
  1. A method that achieves state-of-the-art performance in the robotic warehouse task
@inproceedings{christianos2020shared,
  title={Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning},
  author={Christianos, Filippos and Sch{\"a}fer, Lukas and Albrecht, Stefano V},
  booktitle = {Advances in Neural Information Processing Systems},
  year={2020}
}

About

Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment

Resources

Packages

No packages published

Languages