proroklab/gnngls proroklab/gnngls

  • Stars
    star
    21
  • Rank 1,084,038 (Top 22 %)
  • Language
    Python
  • Created almost 3 years ago
  • Updated almost 2 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
proroklab/gnngls
github

proroklab

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Code accompanying the paper Graph Neural Network Guided Local Search for the Traveling Salesperson Problem

More Repositories

1

VectorizedMultiAgentSimulator

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
Python
312
star
2

gnn_pathplanning

Graph Neural Networks for Decentralized Path Planning
Python
191
star
3

popgym

Partially Observable Process Gym
Python
160
star
4

magat_pathplanning

Python
98
star
5

rllib_differentiable_comms

This is a minimal example to demonstrate how multi-agent reinforcement learning with differentiable communication channels and centralized critics can be realized in RLLib. This example serves as a reference implementation and starting point for making RLLib more compatible with such architectures.
Python
39
star
6

minicar

Python
37
star
7

ros2_multi_agent_passage

Python
35
star
8

HetGPPO

Heterogeneous Multi-Robot Reinforcement Learning
Python
32
star
9

rl_multi_agent_passage

Repository containing RL environment, model and trainer for GNN demo for ICRA 2022 paper "A Framework for Real-World Multi-Robot Systems\\Running Decentralized GNN-Based Policies"
Python
31
star
10

adversarial_comms

Python
30
star
11

ffm

Reinforcement Learning with Fast and Forgetful Memory
Python
23
star
12

DVM-SLAM

Jupyter Notebook
17
star
13

ModGNN

Python
16
star
14

graph-conv-memory

Graph convolutional memory
Python
15
star
15

ControllingBehavioralDiversity

This repository contains the code for Diversity Control (DiCo), a novel method to constrain behavioral diversity in multi-agent reinforcement learning.
Python
12
star
16

cambridge-robomaster

This is the source repository containing all information necessary to reproduce the Cambridge RoboMaster platform.
Python
9
star
17

private_flocking

TeX
7
star
18

task-agnostic-comms

Task-Agnostic Communication for Multi-Agent Reinforcement Learning
Python
4
star
19

resilient-fusion

Python
3
star
20

robomaster_ros2_can

ROS2 driver to control RoboMaster S1 using the internal CAN interface
C++
3
star
21

sensor-guided-visual-nav

Python
3
star
22

xaer

Python
2
star
23

robomaster_sdk_can

C++ library to command the RoboMaster S1 through the internal CAN bus
C++
2
star
24

memory-monoids

Python
2
star