refine config.json

config.json

@@ -11,19 +11,20 @@
     "ending_eps": 0.01,
     "duration_eps": 250000,
     "batch_size": 32,
-    "n_step_return": 5,
     "---- i-DQN ---": "----------------------------",
     "idqn_learning_rate": 6.25e-5,
     "idqn_optimizer_eps": 1.5e-4,
-    "idqn_n_training_steps_per_target_update": 3000000,
-    "idqn_n_training_steps_per_rolling_step": 8000,
+    "idqn_n_step_return": 1,
+    "idqn_n_training_steps_per_target_update": 30,
+    "idqn_n_training_steps_per_window_shift": 6000,
     "idqn_head_behaviorial_policy": "uniform",
     "idqn_shared_network": true,
     "---- i-IQN ---": "----------------------------",
     "iiqn_learning_rate": 0.00005,
     "iiqn_optimizer_eps": 0.0003125,
-    "iiqn_n_training_steps_per_target_update": 3000000,
-    "iiqn_n_training_steps_per_rolling_step": 8000,
+    "iiqn_n_step_return": 3,
+    "iiqn_n_training_steps_per_target_update": 30,
+    "iiqn_n_training_steps_per_window_shift": 6000,
     "iiqn_head_behaviorial_policy": "uniform",
     "iiqn_n_quantiles_policy": 32,
     "iiqn_n_quantiles": 64,