Table 8.

GLean generated plans with networks trained with different meta-priors, compared with ground truth. Note that in order for the results in the following tables to be comparable to the previous experiment, the output values were rescaled to $[0,1]$. Only the sensory states are compared between generated and ground truth trajectories. Best result highlighted in bold.

Meta-Prior	Average ${\mathit{KLD}}_{\mathit{pq}}$	Average RMSE $\pm \mathit{\sigma }$	Average GD $\pm \mathit{\sigma }$
Weak	12.48	$0.0387\pm 0.00067$	$\mathbf{5.7}\times {\mathbf{10}}^{-\mathbf{5}}\pm \mathbf{7.4}\times {\mathbf{10}}^{-\mathbf{6}}$
Intermediate	4.64	$\mathbf{0.0230}\pm \mathbf{0.00058}$	$6.9\times {10}^{-5}\pm 8.6\times {10}^{-6}$
Strong	2.35	$0.0242\pm 0.00051$	$1.3\times {10}^{-4}\pm 1.4\times {10}^{-5}$