Human and Multi-Agent collaboration in a human-MARL teaming framework

2020/06/12 by Neda Navidi, Néda Navidi, Navidi, Neda +14
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG) #Multi-Agent Systems and Negotiation #Multiagent Systems (cs.MA) #Reinforcement Learning in Robotics #Robotic Path Planning Algorithms #cs.AI #cs.HC #cs.LG #cs.MA

paper · pdf · doi:10.48550/arxiv.2006.07301

openalex publication_date 2020/06/12 · arxiv created 2021/03/01 · arxiv updated 2021/03/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Reinforcement learning provides effective results with agents learning from their observations, received rewards, and internal interactions between agents. This study proposes a new open-source MARL framework, called COGMENT, to efficiently leverage human and agent interactions as a source of learning. We demonstrate these innovations by using a designed real-time environment with unmanned aerial vehicles driven by RL agents, collaborating with a human. The results of this study show that the proposed collaborative paradigm and the open-source framework leads to significant reductions in both human effort and exploration costs.

Citations

• Dueling Network Architectures for Deep Reinforcement Learning
• A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

Related

• Human-Machine Teaming for UAVs: An Experimentation Platform
• Human-AI Collaboration in Real-World Complex Environment with Reinforcement Learning
• Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment & Operations
• Advances in Multi-agent Reinforcement Learning: Persistent Autonomy and Robot Learning Lab Report 2024
• Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm