polish(pu): polish hyper-parameters in ptz_pistonball_qmix_config.py

puyuan1996 · Nov 21, 2024 · ffec133 · ffec133
1 parent b4b7029
commit ffec133
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 5 deletions.
diff --git a/dizoo/petting_zoo/config/ptz_pistonball_qmix_config.py b/dizoo/petting_zoo/config/ptz_pistonball_qmix_config.py
@@ -5,7 +5,7 @@
 evaluator_env_num = 8
 
 main_config = dict(
-    exp_name=f'data_pistonball/ptz_pistonball_n{n_pistons}_qmix_reward-norm_nsample16_H5_rbs1e3_seed0',
+    exp_name=f'data_pistonball/ptz_pistonball_n{n_pistons}_qmix_nsample16_H5_reward-norm/20*50_grad-clip-20_upc20_bs32_rbs2e3_seed0',
     env=dict(
         env_family='butterfly',
         env_id='pistonball_v6',
@@ -32,10 +32,12 @@
             mixer=True,
         ),
         learn=dict(
-            update_per_collect=50,
+            update_per_collect=20,
             # update_per_collect=100,
-            batch_size=16,
+            # batch_size=16,
+            batch_size=32,
             learning_rate=0.0001,
+            clip_value=20,
             target_update_theta=0.001,
             discount_factor=0.99,
             double_q=True,
@@ -54,7 +56,8 @@
                 decay=100000,
             ),
             replay_buffer=dict(
-                replay_buffer_size=1000,
+                replay_buffer_size=2000,
+                # replay_buffer_size=5000,
             ),
         ),
     ),

diff --git a/dizoo/petting_zoo/envs/petting_zoo_pistonball_env.py b/dizoo/petting_zoo/envs/petting_zoo_pistonball_env.py
@@ -130,7 +130,8 @@ def step(self, action: np.ndarray) -> BaseEnvTimestep:
         rew_n = rew_n.astype(np.float32)
 
         if self.normalize_reward:
-            rew_n = rew_n / self._num_pistons
+            # TODO: more elegent scale factor
+            rew_n = rew_n / (self._num_pistons*50)
 
         self._eval_episode_return += rew_n.item()