arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07301cs.AIcs.HCcs.LGcs.MA
收藏

人-MARL合作框架中的人与多智能体协作

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

AI Redefined, AI-R Inc.(AI Redefined, AI-R公司)

Neda Navidi, Francoi Chabo, Saga Kurandwa, Iv Lutigma, Vincent Robt, Gregry Szrftgr, Andea Schuh

摘要:

强化学习提供了有效的结果,代理从他们的观察,收到的奖励和代理之间的内部交互中学习。这项研究提出了一个新的开源MARL框架,称为COGMENT,有效地利用人类和代理的互动作为学习的来源。我们通过使用设计的实时环境与RL代理人驱动的无人驾驶飞行器,与人类合作来展示这些创新。这项研究的结果表明,所提出的合作模式和开源框架导致显着减少人力和探索成本。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑