Table 11 Summary of the performance of the RL and benchmark agent showing the mean (\(\mu\)) and standard deviation (\(\sigma\)) for ‘tree_score’ and ‘isTreeCorrectlyAnswered’ metrics.

From: Structured AI decision-making in disaster management

Metric

Type

\(\mu\)

\(\sigma\)

tree_score

RL

1.4

4.49

Benchmark

− 0.3954

11.5218

isTreeCorrectlyAnswered

RL

0.88

0.15

Benchmark

0.8201

0.3841

Back to article page