Table 1 Averaged evaluation metrics of the 15 trained agents, including standard deviation, in comparison with the deterministic baseline applied to the 8028 test steps

Profit \(\phantom {\dot {i}\!}\Phi _{\MakeUppercase {{g}}^{*}}\) [€]

6,529

27,631 ± 3,064

Market share \(\phantom {\dot {i}\!}\sigma _{\MakeUppercase {{g}}^{*}}\) [%]

6.79

9.47 ± 0.43

Overload n_ol

3

2216.2 ±339.85

Undervoltage n_uv

0

3103.27 ± 467.27

Overvoltage n_ov

0

2.07 ± 1.81