arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.09232cs.ROcs.AIcs.LGcs.MA
收藏

利用强化学习自主识别群体任务中智能体的错误来源

Using reinforcement learning to autonomously identify sources of error for agents in group missions

Japan Advanced Institute of Science and Technology (JAIST)(日本先端科学技术大学院大学);Air Force Research Laboratory(美国空军研究实验室)

Keishu Utimula, Ken-taro Hayaschi, Trevor J. Bihl, Kenta Hongo, Ryo Maezono

AI总结:

针对集群智能体故障原因难通过常规通信判断、梯度法因差异函数多为零无法优化行动计划的问题,本研究用Q表强化学习生成自主行动方案,通过智能体碰撞定位故障,验证了该方法的可行性。

摘要:

当智能体集群执行任务时,指挥基地经常观察到部分智能体突发故障。仅依靠指挥基地与涉事智能体之间的通信,通常难以判断故障是由执行器(假设,$h_a$)还是传感器(假设,$h_s$)导致的。然而,通过促成智能体之间的协作,可以识别故障原因;换言之,我们预期对于$h_a$能检测到相应的位移,而对于$h_s$则不能。本研究探讨了人工智能能否自主生成行动计划$\boldsymbol{g}$以精准定位上述故障原因的问题。由于对$\boldsymbol{g}$的预期响应通常取决于所采用的假设[将该差异记为$D(\boldsymbol{g})$],因此可以构建利用$D(\boldsymbol{g})$定位故障原因的公式。尽管使$D(\boldsymbol{g})$最大化的$\boldsymbol{g}^*$是适用于该任务的合适行动计划,但使用传统梯度法难以实现此类优化,因为$D(\boldsymbol{g})$仅在与其他智能体碰撞等罕见事件中才非零,而绝大多数集群动作$\boldsymbol{g}$对应的$D(\boldsymbol{g})=0$。也就是说,在几乎整个$\boldsymbol{g}$空间中,$D(\boldsymbol{g})$的梯度都为零,梯度法并不适用。为解决这一问题,我们使用Q-table(Q表)强化学习构建了行动计划。令人惊讶的是,通过强化学习生成的最优行动计划提出了一种类人解决方案:通过让其他智能体与故障智能体碰撞来定位问题。借助这一简单原型,我们证明了将Q表强化学习方法应用于规划自主行动以定位故障原因的潜力。

英文摘要:

When agents swarm to execute a mission, some of them frequently exhibit sudden failure, as observed from the command base. It is generally difficult to determine whether a failure is caused by actuators (hypothesis, $h_a$) or sensors (hypothesis, $h_s$) by solely relying on the communication between the command base and concerning agent. However, by instigating collusion between the agents, the cause of failure can be identified; in other words, we expect to detect corresponding displacements for $h_a$ but not for $h_s$. In this study, we considered the question as to whether artificial intelligence can autonomously generate an action plan $\boldsymbol{g}$ to pinpoint the cause as aforedescribed. Because the expected response to $\boldsymbol{g}$ generally depends upon the adopted hypothesis [let the difference be denoted by $D(\boldsymbol{g})$], a formulation that uses $D\left(\boldsymbol{g}\right)$ to pinpoint the cause can be made. Although a $\boldsymbol{g}^*$ that maximizes $D(\boldsymbol{g})$ would be a suitable action plan for this task, such an optimization is difficult to achieve using the conventional gradient method, as $D(\boldsymbol{g})$ becomes nonzero in rare events such as collisions with other agents, and most swarm actions $\boldsymbol{g}$ give $D(\boldsymbol{g})=0$. In other words, throughout almost the entire space of $\boldsymbol{g}$, $D(\boldsymbol{g})$ has zero gradient, and the gradient method is not applicable. To overcome this problem, we formulated an action plan using Q-table reinforcement learning. Surprisingly, the optimal action plan generated via reinforcement learning presented a human-like solution to pinpoint the problem by colliding other agents with the failed agent. Using this simple prototype, we demonstrated the potential of applying Q-table reinforcement learning methods to plan autonomous actions to pinpoint the causes of failure.

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。

↑