From 1e56df834c26708db845eb12d00fdaecac7016e0 Mon Sep 17 00:00:00 2001 From: Mats Gottenbos <matsgottenbos@gmail.com> Date: Tue, 19 Jan 2021 23:08:46 +0100 Subject: [PATCH] Added more parameters to hyperparameter tuning --- muzero.py | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/muzero.py b/muzero.py index c07982c..572cafa 100644 --- a/muzero.py +++ b/muzero.py @@ -672,14 +672,27 @@ if __name__ == "__main__": # Parametrization documentation: https://facebookresearch.github.io/nevergrad/parametrization.html muzero.terminate_workers() del muzero + + # This part has custom edits budget = 20 parallel_experiments = 2 - lr_init = nevergrad.p.Log(a_min=0.0001, a_max=0.1) - discount = nevergrad.p.Log(lower=0.95, upper=0.9999) - parametrization = nevergrad.p.Dict(lr_init=lr_init, discount=discount) + num_tests = 20 + + parametrization = nevergrad.p.Dict( + lr_init=nevergrad.p.Log(lower=0.0001, upper=0.1), + discount=nevergrad.p.Log(lower=0.95, upper=0.9999), + stacked_observations=nevergrad.p.Log(lower=1, upper=100).set_integer_casting(), + num_simulations=nevergrad.p.Log(lower=1, upper=200).set_integer_casting(), + batch_size=nevergrad.p.Log(lower=10, upper=200).set_integer_casting(), + checkpoint_interval=nevergrad.p.Log(lower=5, upper=200).set_integer_casting(), + value_loss_weight=nevergrad.p.Log(lower=0.1, upper=0.5), + ) + best_hyperparameters = hyperparameter_search( - game_name, parametrization, budget, parallel_experiments, 20 + game_name, parametrization, budget, parallel_experiments, num_tests ) + # End custom edits + muzero = MuZero(game_name, best_hyperparameters) else: break -- GitLab