FaultBench-Industrial Research documentation
Research documentation ยท Experimental record
Agent dropout / Transient

Rule-based reconfiguration

Transient agent dropout evaluation

Fault: Agent dropout
Duration: Transient
Recovery mechanism: Rule-based reconfiguration

Experiment definition

The experiment evaluates Rule-based reconfiguration under a transient agent dropout injection. Fault onset is randomized between environment steps 40 and 60.

Experimental trajectory graphs

One representative seed (seed 0 of 8) per target combination from the full sweep. See the Results page for the multi-seed aggregate comparison across mechanisms. The graphs for every seed are archived at doi:10.5281/zenodo.23304785 (files available from 10 November 2026).

Rule-based reconfiguration

Expected evaluation record:

MetricRecorded value
Degradation-area5.37 ± 2.19 (corrected; mean ± 95% CI, n=24)
Safety-violation excess21.7 ± 8.6 (weighted, control-subtracted; mean ± 95% CI, n=24)
Fraction of time healthy0.697 ± 0.019 (mean ± 95% CI, n=24)
Relapse count0.50 ± 0.22 (mean ± 95% CI, n=24)
False-recovery rate0.000 ± 0.000 (mean ± 95% CI, n=24)
Intervention recall1.000 ± 0.000 (mean ± 95% CI, n=24)

Values are means with 95% confidence intervals across every target × duration-fixed combination shown on this page (see graphs below), 8 seeds each. See the Results page for the cross-mechanism comparison.

Sorting Agent Target

Agent dropout transient fault, Rule-based reconfiguration, Sorting Agent Target
Rule-based reconfiguration - Sorting Agent Target - evaluation trajectory under transient agent dropout (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.

Pressing Agent Target

Agent dropout transient fault, Rule-based reconfiguration, Pressing Agent Target
Rule-based reconfiguration - Pressing Agent Target - evaluation trajectory under transient agent dropout (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.

Both Agents Target

Agent dropout transient fault, Rule-based reconfiguration, Both Agents Target
Rule-based reconfiguration - Both Agents Target - evaluation trajectory under transient agent dropout (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.

Rule-based detect

Expected evaluation record:

MetricRecorded value
Degradation-area8.04 ± 4.78 (corrected; mean ± 95% CI, n=24)
Safety-violation excess34.3 ± 20.0 (weighted, control-subtracted; mean ± 95% CI, n=24)
Fraction of time healthy0.625 ± 0.030 (mean ± 95% CI, n=24)
Relapse count0.62 ± 0.21 (mean ± 95% CI, n=24)
False-recovery rate0.830 ± 0.047 (mean ± 95% CI, n=24)
Intervention recall0.350 ± 0.075 (mean ± 95% CI, n=24)

Values are means with 95% confidence intervals across every target × duration-fixed combination shown on this page (see graphs below), 8 seeds each. See the Results page for the cross-mechanism comparison.

Sorting Agent Target

Agent dropout transient fault, Rule-based detect, Sorting Agent Target
Rule-based detect - Sorting Agent Target - evaluation trajectory under transient agent dropout (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.

Pressing Agent Target

Agent dropout transient fault, Rule-based detect, Pressing Agent Target
Rule-based detect - Pressing Agent Target - evaluation trajectory under transient agent dropout (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.

Both Agents Target

Agent dropout transient fault, Rule-based detect, Both Agents Target
Rule-based detect - Both Agents Target - evaluation trajectory under transient agent dropout (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.

Notes

This page is intentionally separated from the paper-facing results so that full-resolution plots, additional seeds, and diagnostic figures can be documented without overloading the publication.