
Mean and Std for totalReward:
HyperRNN: Mean = 11.2551, Std = 8.0208
RNNEXP: Mean = 9.1829, Std = 8.5475
RNNIMP: Mean = -0.3862, Std = 11.9829

Tukey HSD results for totalReward:
  Multiple Comparison of Means - Tukey HSD, FWER=0.05  
=======================================================
 group1  group2 meandiff p-adj  lower    upper   reject
-------------------------------------------------------
HyperRNN RNNEXP  -2.0722   0.0   -2.901  -1.2434   True
HyperRNN RNNIMP -11.6413   0.0   -12.47 -10.8125   True
  RNNEXP RNNIMP  -9.5691   0.0 -10.3978  -8.7403   True
-------------------------------------------------------

Pairwise p-values:
[1.47033559e-08 9.19375687e-13 9.19375687e-13]

Mean and Std for totalSteps:
HyperRNN: Mean = 56.8740, Std = 13.2913
RNNEXP: Mean = 60.0107, Std = 12.4216
RNNIMP: Mean = 66.7860, Std = 9.4322

Tukey HSD results for totalSteps:
Multiple Comparison of Means - Tukey HSD, FWER=0.05 
====================================================
 group1  group2 meandiff p-adj lower   upper  reject
----------------------------------------------------
HyperRNN RNNEXP   3.1367   0.0 2.1235  4.1498   True
HyperRNN RNNIMP    9.912   0.0 8.8988 10.9252   True
  RNNEXP RNNIMP   6.7753   0.0 5.7622  7.7885   True
----------------------------------------------------

Pairwise p-values:
[2.29849473e-12 9.19375687e-13 9.19375687e-13]

Mean and Std for totalCollisions:
HyperRNN: Mean = 0.0133, Std = 0.1147
RNNEXP: Mean = 0.0167, Std = 0.1280
RNNIMP: Mean = 0.0333, Std = 0.1795

Tukey HSD results for totalCollisions:
Multiple Comparison of Means - Tukey HSD, FWER=0.05 
====================================================
 group1  group2 meandiff p-adj  lower  upper  reject
----------------------------------------------------
HyperRNN RNNEXP   0.0033 0.8003 -0.009 0.0156  False
HyperRNN RNNIMP     0.02 0.0004 0.0077 0.0323   True
  RNNEXP RNNIMP   0.0167 0.0042 0.0044  0.029   True
----------------------------------------------------

Pairwise p-values:
[8.00274636e-01 4.04046348e-04 4.23244145e-03]

Mean and Std for totalBoundary:
HyperRNN: Mean = 0.0013, Std = 0.0365
RNNEXP: Mean = 0.0040, Std = 0.0631
RNNIMP: Mean = 0.0047, Std = 0.0682

Tukey HSD results for totalBoundary:
 Multiple Comparison of Means - Tukey HSD, FWER=0.05 
=====================================================
 group1  group2 meandiff p-adj   lower  upper  reject
-----------------------------------------------------
HyperRNN RNNEXP   0.0027  0.414 -0.0023 0.0076  False
HyperRNN RNNIMP   0.0033 0.2527 -0.0016 0.0083  False
  RNNEXP RNNIMP   0.0007 0.9462 -0.0043 0.0056  False
-----------------------------------------------------

Pairwise p-values:
[0.41398572 0.25274969 0.94619884]
