Data

Tools

Indexes

Applications

Experiments

Open Source Science

gym-marl-reconnaissance

Gym environment for cooperative multi-agent reinforcement learning in heterogeneous robot teams

https://github.com/jacopopan/gym-marl-reconnaissance

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ✓
    Committers with academic emails
    1 of 1 committers (100.0%) from academic institutions
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.6%) to scientific vocabulary

Keywords

coordination gym heterogeneous multi-agent multi-robot non-stationary pybullet reinforcement-learning
Last synced: 6 months ago · JSON representation ·

Repository

Gym environment for cooperative multi-agent reinforcement learning in heterogeneous robot teams

Basic Info
  • Host: GitHub
  • Owner: JacopoPan
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 24 MB
Statistics
  • Stars: 46
  • Watchers: 3
  • Forks: 4
  • Open Issues: 0
  • Releases: 0
Topics
coordination gym heterogeneous multi-agent multi-robot non-stationary pybullet reinforcement-learning
Created over 4 years ago · Last pushed about 4 years ago
Metadata Files
Readme License Citation

README.md

gym-marl-reconnaissance

Gym environments for heterogeneous multi-agent reinforcement learning in non-stationary worlds

This repository's master branch is work in progress, please git pull frequently and feel free to open new issues for any undesired, unexpected, or (presumably) incorrect behavior. Thanks 🙏

Also see how to programmatically control real RoboMaster hardware (S1 UGV, Tello Talent UAV) in Python here

figure

Install on Ubuntu/macOS

(optional) Create and access a Python 3.7 environment using conda $ conda create -n recon python=3.7 # Create environment (named 'recon' here) $ conda activate recon # Activate environment 'recon' Clone and install the gym-marl-reconnaissance repository $ git clone https://github.com/JacopoPan/gym-marl-reconnaissance # Clone repository $ cd gym-marl-reconnaissance # Enter the repository $ pip install -e . # Install the repository

Configure

Set the parameters of the simulation environment seed: -1 ctrl_freq: 2 pyb_freq: 30 gui: False record: False episode_length_sec: 30 action_type: 'task_assignment' # Alternatively, 'tracking' obs_type: 'global' reward_choice: 'reward_c' adv_type: 'avoidant' # Alternatively, 'blind' visibility_threshold: 12 setup: edge: 10 obstacles: 0 tt: 1 s1: 1 adv: 2 neu: 1 debug: False

figure figure

Use

Step an environment with random action inputs $ python3 ./experiments/debug.py --random True Step an environment with a greedy policy (only for task_assignment) $ python3 ./experiments/debug.py Learn using stable-baselines3 $ python3 ./experiments/train.py --algo <a2c | ppo> --yaml <filname in ./experiments/configurations/> Replay a trained agent $ python3 ./experiments/test.py --exp ./results/exp--<algo>--<config>--<date>_<time>

Results

Task assignment (1 UAV and 1 UGV vs 2 targets and 1 neutral)

figure

Tracking (1 UAV or 1 UGV vs 1 target, with or without 1 neutral)

figure

University of Toronto's Dynamic Systems Lab / Vector Institute / Mitacs

Owner

  • Name: Jacopo Panerati
  • Login: JacopoPan
  • Kind: user

Went to the desert—formerly @utiasDSL, @VectorInstitute, @proroklab, @MISTLab

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Panerati"
  given-names: "Jacopo"
  orcid: "https://orcid.org/0000-0003-2994-5422"
title: "gym-marl-reconnaissance"
version: 0.0.1
doi: 10.5281/zenodo.1234
date-released: 2021-09-04
url: "https://github.com/JacopoPan/gym-marl-reconnaissance"

GitHub Events

Total
  • Watch event: 7
Last Year
  • Watch event: 7

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 26
  • Total Committers: 1
  • Avg Commits per committer: 26.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Jacopo Panerati j****i@u****a 26
Committer Domains (Top 20 + Academic)
utoronto.ca: 1

Issues and Pull Requests

Last synced: 8 months ago

All Time
  • Total issues: 3
  • Total pull requests: 0
  • Average time to close issues: 8 days
  • Average time to close pull requests: N/A
  • Total issue authors: 2
  • Total pull request authors: 0
  • Average comments per issue: 1.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • Tie-1 (1)
  • hit-JB (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels