proroklab

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...

proroklab

proroklab

Graph Neural Networks for Decentralized Path Planning

proroklab

proroklab

proroklab

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 re...

proroklab

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"

proroklab

Partially Observable Process Gym

proroklab

Heterogeneous Multi-Robot Reinforcement Learning

proroklab