change arm to push the ground reward function
This commit is contained in:
@@ -45,7 +45,7 @@ params:
|
||||
lr_schedule: adaptive
|
||||
kl_threshold: 0.008
|
||||
score_to_win: 20000
|
||||
max_epochs: 500000
|
||||
max_epochs: 1000000
|
||||
save_best_after: 50
|
||||
save_frequency: 100
|
||||
grad_norm: 0.5
|
||||
|
||||
Reference in New Issue
Block a user