Benchmarks Results:
API:
ConstrainedREPS: eps: 0.5 kappa: 0.1 n_episodes_per_fit: 25 PGPE: alpha: 0.3 n_episodes_per_fit: 25 REPS: eps: 0.5 n_episodes_per_fit: 25 RWR: beta: 0.01 n_episodes_per_fit: 25
GPOMDP: alpha: 0.01 n_episodes_per_fit: 25 REINFORCE: alpha: 0.01 n_episodes_per_fit: 25 eNAC: alpha: 0.01 n_episodes_per_fit: 25