update

reinforce_tune_lr.py

@@ -19,4 +19,4 @@ for run_id, (policy_lr, value_lr) in enumerate(product(*param_values)):
     print('Policy learning rate: ', policy_lr)
     print('Value learning rate: ', value_lr)
     os.system(
-        f"python train_reinforce.py --save_path {run_id + 1} --n_hidden 128 --lr_policy {policy_lr} --lr_value {value_lr} --n_episode 200 ")
+        f"python train_reinforce.py --save_path {run_id + 1} --n_hidden 128 --lr_policy {policy_lr} --lr_value {value_lr} --n_episode 50000 ")