You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Auto-Multilift is a novel learning framework for cooperative load transportation with quadrotors. It can automatically tune various MPC hyperparameters, which are modeled by DNNs and difficult to tune manually, via reinforcement learning in a distributed and closed-loop manner.
The Drone Swarm Search project provides an environment for SAR missions built on PettingZoo, where agents, represented by drones, are tasked with locating targets identified as shipwrecked individuals.
The TTCP CAGE Challenges are a series of public challenges instigated to foster the development of autonomous cyber defensive agents. This CAGE Challenge 4 (CC4) returns to a defence industry enterprise environment, and introduces a Multi-Agent Reinforcement Learning (MARL) scenario.
This repository contains Dongming Shen's demonstration code and documentation for the research projects conducted at the IDM Lab, USC. The project focuses on integrating Multi-Agent Path Finding (MAPF) with Multi-Agent Reinforcement Learning (MARL) to explore efficient coordination strategies among autonomous agents in dynamic environments.
MARL explores cooperation & competition in gridworlds. Batman & Robin team up (DQN, CQL, MAD-DQN, REINFORCE). Adversaries use MADDPG with CLDE for strategy.
This program aims to compare the performance of the Multiagent Rollout algorithm against the Ordinary Rollout algorithm and the Base Policy in the context of the Spiders and Flies problem.
This repository presents a multi-agent reinforcement learning approach for energy-efficient collaborative control of base stations in 5G massive MIMO cellular networks.