Push agent to the Hub
Browse files- README.md +2 -2
- logs/events.out.tfevents.1732920424.fb28a0c4b3f0.9849.0 +3 -0
- model.pt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -17,7 +17,7 @@ model-index:
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
-
value: -
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
@@ -38,7 +38,7 @@ model-index:
|
|
| 38 |
'capture_video': False
|
| 39 |
'repo_id': 'paranke/ppo-LunarLander-from-scratch'
|
| 40 |
'env_id': 'LunarLander-v2'
|
| 41 |
-
'total_timesteps':
|
| 42 |
'learning_rate': 2.5e-05
|
| 43 |
'num_envs': 8
|
| 44 |
'num_steps': 512
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -188.84 +/- 109.07
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 38 |
'capture_video': False
|
| 39 |
'repo_id': 'paranke/ppo-LunarLander-from-scratch'
|
| 40 |
'env_id': 'LunarLander-v2'
|
| 41 |
+
'total_timesteps': 131072
|
| 42 |
'learning_rate': 2.5e-05
|
| 43 |
'num_envs': 8
|
| 44 |
'num_steps': 512
|
logs/events.out.tfevents.1732920424.fb28a0c4b3f0.9849.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45d61be514908438777e76b12529f8c9127f20026062c7a2a1ea6c1343b7eb92
|
| 3 |
+
size 183288
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43026
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa714b9d9f6c7c0d05207a641f83a410fa946e57394cd0c745f3c3e14278d479
|
| 3 |
size 43026
|
replay.mp4
CHANGED
|
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"env_id": "LunarLander-v2", "mean_reward": -
|
|
|
|
| 1 |
+
{"env_id": "LunarLander-v2", "mean_reward": -188.83851961617967, "std_reward": 109.0729111961388, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-29T22:48:08.563984"}
|