pushing model
Browse files- README.md +1 -1
- events.out.tfevents.1704463261.4090-171.157279.0 → events.out.tfevents.1705702862.3090-172.2625280.0 +2 -2
- ppo_fix_continuous_action.cleanrl_model +0 -0
- ppo_fix_continuous_action.py +1 -1
- replay.mp4 +0 -0
- videos/Humanoid-v4__ppo_fix_continuous_action__5__1704463253-eval/rl-video-episode-0.mp4 +0 -0
- videos/Humanoid-v4__ppo_fix_continuous_action__5__1704463253-eval/rl-video-episode-1.mp4 +0 -0
- videos/Humanoid-v4__ppo_fix_continuous_action__5__1704463253-eval/rl-video-episode-8.mp4 +0 -0
- videos/Humanoid-v4__ppo_fix_continuous_action__5__1705702854-eval/rl-video-episode-0.mp4 +0 -0
- videos/Humanoid-v4__ppo_fix_continuous_action__5__1705702854-eval/rl-video-episode-1.mp4 +0 -0
- videos/Humanoid-v4__ppo_fix_continuous_action__5__1705702854-eval/rl-video-episode-8.mp4 +0 -0
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
type: Humanoid-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
16 |
type: Humanoid-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 698.23 +/- 83.72
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
events.out.tfevents.1704463261.4090-171.157279.0 → events.out.tfevents.1705702862.3090-172.2625280.0
RENAMED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bda760451e65180a8252fee198378463cd4b2305644c4198c9a22d628a052f0f
|
3 |
+
size 1560873
|
ppo_fix_continuous_action.cleanrl_model
CHANGED
Binary files a/ppo_fix_continuous_action.cleanrl_model and b/ppo_fix_continuous_action.cleanrl_model differ
|
|
ppo_fix_continuous_action.py
CHANGED
@@ -198,7 +198,7 @@ class NormalizeReward(gym.core.Wrapper, gym.utils.RecordConstructorArgs):
|
|
198 |
return obs, rews, terminateds, truncateds, infos
|
199 |
|
200 |
def reset(self, **kwargs):
|
201 |
-
self.returns = np.zeros(self.num_envs)
|
202 |
return self.env.reset(**kwargs)
|
203 |
|
204 |
def normalize(self, rews):
|
|
|
198 |
return obs, rews, terminateds, truncateds, infos
|
199 |
|
200 |
def reset(self, **kwargs):
|
201 |
+
# self.returns = np.zeros(self.num_envs)
|
202 |
return self.env.reset(**kwargs)
|
203 |
|
204 |
def normalize(self, rews):
|
replay.mp4
CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
videos/Humanoid-v4__ppo_fix_continuous_action__5__1704463253-eval/rl-video-episode-0.mp4
DELETED
Binary file (301 kB)
|
|
videos/Humanoid-v4__ppo_fix_continuous_action__5__1704463253-eval/rl-video-episode-1.mp4
DELETED
Binary file (271 kB)
|
|
videos/Humanoid-v4__ppo_fix_continuous_action__5__1704463253-eval/rl-video-episode-8.mp4
DELETED
Binary file (297 kB)
|
|
videos/Humanoid-v4__ppo_fix_continuous_action__5__1705702854-eval/rl-video-episode-0.mp4
ADDED
Binary file (243 kB). View file
|
|
videos/Humanoid-v4__ppo_fix_continuous_action__5__1705702854-eval/rl-video-episode-1.mp4
ADDED
Binary file (234 kB). View file
|
|
videos/Humanoid-v4__ppo_fix_continuous_action__5__1705702854-eval/rl-video-episode-8.mp4
ADDED
Binary file (242 kB). View file
|
|