Artifacts from deterministic distribution?

blakeelias / pandemic_RL

Reinforcement learning for economically optimal pandemic response.

GNU General Public License v3.0

1 stars 1 forks source link

Open blakeelias opened 3 years ago

blakeelias commented 3 years ago

Does this behavior look right?

Horizontal bands here seem suspect:

Deterministic, horizon = 92, intervention period = 1 step:

Deterministic, horizon = 92, intervention period = 2 steps:

blakeelias commented 3 years ago

Intervention period = 4 steps:

This looks reasonable.