change model
This commit is contained in:
@@ -41,11 +41,11 @@ params:
|
||||
normalize_advantage: True
|
||||
gamma: 0.96
|
||||
tau: 0.95
|
||||
learning_rate: 5e-4
|
||||
learning_rate: 3e-4
|
||||
lr_schedule: adaptive
|
||||
kl_threshold: 0.008
|
||||
score_to_win: 20000
|
||||
max_epochs: 1000000
|
||||
max_epochs: 200
|
||||
save_best_after: 50
|
||||
save_frequency: 100
|
||||
grad_norm: 0.5
|
||||
|
||||
Reference in New Issue
Block a user