proroklab's repositories
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 Planning
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.
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"
graph-conv-memory
Graph convolutional memory
ControllingBehavioralDiversity
This repository contains the code for Diversity Control (DiCo), a novel method to constrain behavioral diversity in multi-agent reinforcement learning.
cambridge-robomaster
This is the source repository containing all information necessary to reproduce the Cambridge RoboMaster platform.
task-agnostic-comms
Task-Agnostic Communication for Multi-Agent Reinforcement Learning
robomaster_ros2_can
ROS2 driver to control RoboMaster S1 using the internal CAN interface
robomaster_sdk_can
C++ library to command the RoboMaster S1 through the internal CAN bus
ros2_point_robot_simulator
A simple ROS2 point simulator