English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

When agents swarm to execute a mission, some of them frequently exhibitsudden failure, as observed from the command base. It is generally difficult todetermine whether a failure is caused by actuators (hypothesis, $h_a$) orsensors (hypothesis, $h_s$) by solely relying on the communication between thecommand base and concerning agent. However, by instigating collusion betweenthe agents, the cause of failure can be identified; in other words, we expectto detect corresponding displacements for $h_a$ but not for $h_s$. In thisstudy, we considered the question as to whether artificial intelligence canautonomously generate an action plan $\boldsymbol{g}$ to pinpoint the cause asaforedescribed. Because the expected response to $\boldsymbol{g}$ generallydepends upon the adopted hypothesis [let the difference be denoted by$D(\boldsymbol{g})$], a formulation that uses $D\left(\boldsymbol{g}\right)$ topinpoint the cause can be made. Although a $\boldsymbol{g}^*$ that maximizes$D(\boldsymbol{g})$ would be a suitable action plan for this task, such anoptimization is difficult to achieve using the conventional gradient method, as$D(\boldsymbol{g})$ becomes nonzero in rare events such as collisions withother 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 gradientmethod is not applicable. To overcome this problem, we formulated an actionplan using Q-table reinforcement learning. Surprisingly, the optimal actionplan generated via reinforcement learning presented a human-like solution topinpoint the problem by colliding other agents with the failed agent. Usingthis simple prototype, we demonstrated the potential of applying Q-tablereinforcement learning methods to plan autonomous actions to pinpoint thecauses of failure.

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