Human and Multi-Agent collaboration in a human-MARL teaming framework
This addresses the challenge of efficient human-agent collaboration in MARL systems, though it appears incremental as it builds on existing MARL concepts with a new framework.
The study tackled the problem of integrating human and multi-agent reinforcement learning (MARL) by proposing COGMENT, an open-source framework for human-MARL teaming, and demonstrated it with unmanned aerial vehicles, resulting in significant reductions in human effort and exploration costs.
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.