huangfu/InteractionImitation
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add value dice ray config

Browse Source
This commit is contained in:
Johannes Fischer
2021-08-05 18:33:34 +02:00
parent 8bce5d15f6
commit bf4c19a4d0
2 changed files with 80 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
experiments/experiment.py
View File

@@ -90,6 +90,9 @@ def get_full_config(ray_config:dict, method:str)->dict:
if method == 'bc':
from src.bc import bc_config
config = bc_config(ray_config)
elif method == 'vd':
from src.value_dice import vd_config
config = vd_config(ray_config)
else:
raise NotImplementedError
return config
@@ -118,6 +121,25 @@ def get_ray_config(method:str)->dict:
"head_hidden_dim": tune.lograndint(16,257),
"head_final_activation": tune.choice(['sigmoid', None]),
}
elif method == 'vd':
ray_config = {
"policy_lr": tune.loguniform(1e-5, 1e-3),
"value_lr": tune.loguniform(1e-5, 1e-3),
"policy_weight_decay": tune.choice([0, 0.1]),
"value_weight_decay": tune.choice([0, 0.1]),
"train_batch_size": tune.choice([16,32,64]),
"deepsets_phi_hidden_n": tune.randint(1,5),
"deepsets_phi_hidden_dim": tune.lograndint(8,65),
"deepsets_latent_dim": tune.lograndint(8,129),
"deepsets_rho_hidden_n": tune.randint(0,3),
"deepsets_rho_hidden_dim": tune.lograndint(8,129),
"deepsets_output_dim": tune.lograndint(4,129),
"head_hidden_n": tune.randint(1,6),
"head_hidden_dim": tune.lograndint(16,257),
"head_final_activation": tune.choice(['sigmoid', None]),
"clip_grad_norm": tune.choice([.5, 1., 5., 10.]),
"discount": tune.choice([.95, .99])
}
else:
raise NotImplementedError
return ray_config