Analysis of BC hyperparameters

For each environment, we sample 1000 different configurations of hyperparameters at random, and report statistics over the configurations.

Success rate learning curves

Hyperparameters influence breakdown

For each hyperparameter, we aggregate all configurations for each possible value of the hyperparameter and compute the following statistic:
the average of final success rate for the top 50% of configurations (since poorly performing configurations are uninformative). Some
plot bars are "missing", it is because the success rate is 0 for all configurations.

Analysis of number of layers

Analysis of number of units per layer

Analysis of activation function

Analysis of input dropout rate

Analysis of hidden dropout rate

Analysis of optimizer learning rate

Analysis of optimizer weight decay

Analysis of observation normalization