The experiment evaluates Rule-based reconfiguration under a permanent actuator degradation injection. Fault onset is randomized between environment steps 40 and 60.
Experimental trajectory graphs
One representative seed (seed 0 of 8) per target × mode 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:
Metric
Recorded value
Degradation-area
18.26 ± 3.42 (corrected; mean ± 95% CI, n=72)
Safety-violation excess
100.6 ± 19.3 (weighted, control-subtracted; mean ± 95% CI, n=72)
Fraction of time healthy
0.622 ± 0.021 (mean ± 95% CI, n=72)
Relapse count
0.17 ± 0.09 (mean ± 95% CI, n=72)
False-recovery rate
0.000 ± 0.000 (mean ± 95% CI, n=72)
Intervention recall
1.000 ± 0.000 (mean ± 95% CI, n=72)
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 (restrict mode)
Rule-based reconfiguration - Sorting Agent Target (restrict mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Pressing Agent Target (restrict mode)
Rule-based reconfiguration - Pressing Agent Target (restrict mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Both Agents Target (restrict mode)
Rule-based reconfiguration - Both Agents Target (restrict mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Sorting Agent Target (slip mode)
Rule-based reconfiguration - Sorting Agent Target (slip mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Pressing Agent Target (slip mode)
Rule-based reconfiguration - Pressing Agent Target (slip mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Both Agents Target (slip mode)
Rule-based reconfiguration - Both Agents Target (slip mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Sorting Agent Target (stuck mode)
Rule-based reconfiguration - Sorting Agent Target (stuck mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Pressing Agent Target (stuck mode)
Rule-based reconfiguration - Pressing Agent Target (stuck mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Both Agents Target (stuck mode)
Rule-based reconfiguration - Both Agents Target (stuck mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Rule-based detect
Expected evaluation record:
Metric
Recorded value
Degradation-area
24.64 ± 4.05 (corrected; mean ± 95% CI, n=72)
Safety-violation excess
111.7 ± 19.0 (weighted, control-subtracted; mean ± 95% CI, n=72)
Fraction of time healthy
0.542 ± 0.028 (mean ± 95% CI, n=72)
Relapse count
0.40 ± 0.17 (mean ± 95% CI, n=72)
False-recovery rate
0.015 ± 0.007 (mean ± 95% CI, n=72)
Intervention recall
0.411 ± 0.047 (mean ± 95% CI, n=72)
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 (restrict mode)
Rule-based detect - Sorting Agent Target (restrict mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Pressing Agent Target (restrict mode)
Rule-based detect - Pressing Agent Target (restrict mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Both Agents Target (restrict mode)
Rule-based detect - Both Agents Target (restrict mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Sorting Agent Target (slip mode)
Rule-based detect - Sorting Agent Target (slip mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Pressing Agent Target (slip mode)
Rule-based detect - Pressing Agent Target (slip mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Both Agents Target (slip mode)
Rule-based detect - Both Agents Target (slip mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Sorting Agent Target (stuck mode)
Rule-based detect - Sorting Agent Target (stuck mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Pressing Agent Target (stuck mode)
Rule-based detect - Pressing Agent Target (stuck mode) - evaluation trajectory under permanent actuator degradation (fault onset randomized between steps 40-60), seed 0 of the 8-seed sweep.
Both Agents Target (stuck mode)
Rule-based detect - Both Agents Target (stuck mode) - evaluation trajectory under permanent actuator degradation (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.
