From 6326529c2d6d42aee17448621af6e3bf1c25d19a Mon Sep 17 00:00:00 2001
From: "Yinmin.Zhang" <40760801+YinminZhang@users.noreply.github.com>
Date: Fri, 27 Aug 2021 14:13:33 +0800
Subject: [PATCH] fix(zym): modify default setting in mujoco (#35)

---
 dizoo/mujoco/envs/mujoco_wrappers.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/dizoo/mujoco/envs/mujoco_wrappers.py b/dizoo/mujoco/envs/mujoco_wrappers.py
index 0a8b4193..fea48255 100644
--- a/dizoo/mujoco/envs/mujoco_wrappers.py
+++ b/dizoo/mujoco/envs/mujoco_wrappers.py
@@ -1,10 +1,12 @@
+from typing import Dict
 import gym
 import numpy as np
 
 from ding.envs import ObsNormEnv, RewardNormEnv
 
 
-def wrap_mujoco(env_id, norm_obs=True, norm_reward=True, only_info=False) -> gym.Env:
+def wrap_mujoco(env_id, norm_obs: Dict=dict(use_norm=False, ), 
+                norm_reward: Dict=dict(use_norm=False, ), only_info=False) -> gym.Env:
     r"""
     Overview:
         Wrap Mujoco Env to preprocess env step's return info, e.g. observation normalization, reward normalization, etc.
@@ -28,5 +30,5 @@ def wrap_mujoco(env_id, norm_obs=True, norm_reward=True, only_info=False) -> gym
         if norm_obs is not None and norm_obs.use_norm:
             wrapper_info = ObsNormEnv.__name__ + '\n'
         if norm_reward is not None and norm_reward.use_norm:
-            wrapper_info = RewardNormEnv.__name__ + '\n'
+            wrapper_info += RewardNormEnv.__name__ + '\n'
         return wrapper_info
-- 
GitLab