polish(nyz): add metadrive version info

opendilab · Aug 3, 2024 · 3f6cb5a · 3f6cb5a
1 parent 5de52bc
commit 3f6cb5a
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 3 deletions.
diff --git a/README.md b/README.md
@@ -144,7 +144,8 @@ The environments and algorithms currently supported by LightZero are shown in th
 | MiniGrid      | ---      | ✔     | ✔          | ✔               | 🔒         | 🔒             |✔|🔒             |
 | Bsuite        | ---      | ✔     | ✔          | ✔               | 🔒         | 🔒             |✔|🔒             |
 | Memory        | ---      | ✔     | ✔          | ✔               | 🔒         | 🔒             |✔|🔒             |
-| SumToThree (billiards) | ---      | 🔒     | 🔒          | ✔               | 🔒         | 🔒             |🔒|🔒             |
+| SumToThree (billiards) | ---      | 🔒        | 🔒          | ✔               | 🔒         | 🔒             |🔒|🔒             |
+| MetaDrive     | ---      | 🔒     | 🔒        | ✔               | 🔒         | 🔒             | 🔒 |🔒             |
 
 
 <sup>(1): "✔" means that the corresponding item is finished and well-tested.</sup>

diff --git a/zoo/metadrive/README.md b/zoo/metadrive/README.md
@@ -0,0 +1,5 @@
+# Installation
+```shell
+pip install metadrive-simulator==0.3.0.1
+pip install panda3d-simplepbr==0.9
+```
diff --git a/zoo/metadrive/env/drive_env.py b/zoo/metadrive/env/drive_env.py
@@ -281,7 +281,7 @@ def reward_function(self, vehicle_id: str):
 
         reward = 0.0
         reward += self.config["driving_reward"] * (long_now - long_last) * lateral_factor * positive_road
-        reward += self.config["speed_reward"] * (vehicle.speed / vehicle.max_speed) * positive_road
+        reward += self.config["speed_reward"] * (vehicle.speed / vehicle.max_speed_km_h) * positive_road
 
         step_info["step_reward"] = reward
 
@@ -391,4 +391,4 @@ def get_navigation_len(self, vehicle):
         if hasattr(vehicle.navigation, 'u_turn_case'):
             if vehicle.navigation.u_turn_case is True:
                 total_dist += 35
-        return total_dist
+        return total_dist