There are no reviews yet. Be the first to send feedback to the community and the maintainers!
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.gnn_pathplanning
Graph Neural Networks for Decentralized Path Planningpopgym
Partially Observable Process Gymmagat_pathplanning
minicar
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.ros2_multi_agent_passage
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"adversarial_comms
HetGPPO
Heterogeneous Multi-Robot Reinforcement Learningffm
Reinforcement Learning with Fast and Forgetful Memorygnngls
Code accompanying the paper Graph Neural Network Guided Local Search for the Traveling Salesperson ProblemModGNN
ControllingBehavioralDiversity
This repository contains the code for Diversity Control (DiCo), a novel method to constrain behavioral diversity in multi-agent reinforcement learning.private_flocking
cambridge-robomaster
This is the source repository containing all information necessary to reproduce the Cambridge RoboMaster platform.resilient-fusion
sensor-guided-visual-nav
task-agnostic-comms
Task-Agnostic Communication for Multi-Agent Reinforcement Learningxaer
robomaster_ros2_can
ROS2 driver to control RoboMaster S1 using the internal CAN interfacememory-monoids
robomaster_sdk_can
C++ library to command the RoboMaster S1 through the internal CAN busLove Open Source and this site? Check out how you can help us