From 20370357cc842f72e8a5ec630c904790914a486b Mon Sep 17 00:00:00 2001
From: niuyazhe <niuyazhe314@outlook.com>
Date: Fri, 19 Jul 2024 16:40:31 +0800
Subject: [PATCH] polish(nyz): remove unused config fields in mujoco PPO

---
 dizoo/mujoco/config/ant_onppo_config.py         | 3 ---
 dizoo/mujoco/config/halfcheetah_onppo_config.py | 4 +---
 dizoo/mujoco/config/hopper_onppo_config.py      | 4 +---
 dizoo/mujoco/config/walker2d_onppo_config.py    | 2 --
 dizoo/mujoco/envs/mujoco_env.py                 | 1 -
 5 files changed, 2 insertions(+), 12 deletions(-)

diff --git a/dizoo/mujoco/config/ant_onppo_config.py b/dizoo/mujoco/config/ant_onppo_config.py
index 32793ffecc..036d651391 100644
--- a/dizoo/mujoco/config/ant_onppo_config.py
+++ b/dizoo/mujoco/config/ant_onppo_config.py
@@ -5,13 +5,10 @@
     exp_name="ant_onppo_seed0",
     env=dict(
         env_id='Ant-v3',
-        norm_obs=dict(use_norm=False, ),
-        norm_reward=dict(use_norm=False, ),
         collector_env_num=10,
         evaluator_env_num=10,
         n_evaluator_episode=10,
         stop_value=6000,
-        manager=dict(shared_memory=False, )
     ),
     policy=dict(
         cuda=True,
diff --git a/dizoo/mujoco/config/halfcheetah_onppo_config.py b/dizoo/mujoco/config/halfcheetah_onppo_config.py
index f63f296167..b7646bbede 100644
--- a/dizoo/mujoco/config/halfcheetah_onppo_config.py
+++ b/dizoo/mujoco/config/halfcheetah_onppo_config.py
@@ -7,8 +7,6 @@
     exp_name='halfcheetah_onppo_seed0',
     env=dict(
         env_id='HalfCheetah-v3',
-        norm_obs=dict(use_norm=False, ),
-        norm_reward=dict(use_norm=False, ),
         collector_env_num=collector_env_num,
         evaluator_env_num=evaluator_env_num,
         n_evaluator_episode=8,
@@ -78,4 +76,4 @@
 if __name__ == "__main__":
     # or you can enter `ding -m serial_onpolicy -c halfcheetah_onppo_config.py -s 0`
     from ding.entry import serial_pipeline_onpolicy
-    serial_pipeline_onpolicy((main_config, create_config), seed=0)
\ No newline at end of file
+    serial_pipeline_onpolicy((main_config, create_config), seed=0)
diff --git a/dizoo/mujoco/config/hopper_onppo_config.py b/dizoo/mujoco/config/hopper_onppo_config.py
index 0853aa4abb..6d1c57e70e 100644
--- a/dizoo/mujoco/config/hopper_onppo_config.py
+++ b/dizoo/mujoco/config/hopper_onppo_config.py
@@ -5,15 +5,13 @@
     exp_name='hopper_onppo_seed0',
     env=dict(
         env_id='Hopper-v3',
-        norm_obs=dict(use_norm=False, ),
-        norm_reward=dict(use_norm=False, ),
         collector_env_num=8,
         evaluator_env_num=10,
         n_evaluator_episode=10,
         stop_value=4000,
     ),
     policy=dict(
-        cuda=False,
+        cuda=True,
         recompute_adv=True,
         action_space='continuous',
         model=dict(
diff --git a/dizoo/mujoco/config/walker2d_onppo_config.py b/dizoo/mujoco/config/walker2d_onppo_config.py
index 2437d62e43..58f5e9054f 100644
--- a/dizoo/mujoco/config/walker2d_onppo_config.py
+++ b/dizoo/mujoco/config/walker2d_onppo_config.py
@@ -7,8 +7,6 @@
     exp_name='walker2d_onppo_seed0',
     env=dict(
         env_id='Walker2d-v3',
-        norm_obs=dict(use_norm=False, ),
-        norm_reward=dict(use_norm=False, ),
         collector_env_num=collector_env_num,
         evaluator_env_num=evaluator_env_num,
         n_evaluator_episode=8,
diff --git a/dizoo/mujoco/envs/mujoco_env.py b/dizoo/mujoco/envs/mujoco_env.py
index c150581a5b..700142583b 100644
--- a/dizoo/mujoco/envs/mujoco_env.py
+++ b/dizoo/mujoco/envs/mujoco_env.py
@@ -151,7 +151,6 @@ def create_collector_env_cfg(cfg: dict) -> List[dict]:
     def create_evaluator_env_cfg(cfg: dict) -> List[dict]:
         evaluator_cfg = copy.deepcopy(cfg)
         evaluator_env_num = evaluator_cfg.pop('evaluator_env_num', 1)
-        evaluator_cfg.norm_reward.use_norm = False
         return [evaluator_cfg for _ in range(evaluator_env_num)]
 
     @property