Push agent to the Hub
Browse files- README.md +6 -6
- logs/events.out.tfevents.1737225772.15778017b4a9.12115.0 +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 |
---
|
@@ -37,10 +37,10 @@ model-index:
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
-
'total_timesteps':
|
41 |
'learning_rate': 0.00025
|
42 |
-
'num_envs':
|
43 |
-
'num_steps':
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
@@ -55,7 +55,7 @@ model-index:
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'jensenwiedler/ppo-LunarLander-v2-unit8'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: 11.62 +/- 80.51
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
+
'total_timesteps': 1000000
|
41 |
'learning_rate': 0.00025
|
42 |
+
'num_envs': 4
|
43 |
+
'num_steps': 128
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'jensenwiedler/ppo-LunarLander-v2-unit8'
|
58 |
+
'batch_size': 512
|
59 |
+
'minibatch_size': 128}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1737225772.15778017b4a9.12115.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e94b7fee620b9f1b222da9b07dd4af10a0f7e39468fb18855709f3b25573b5d3
|
3 |
+
size 1255280
|
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:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
|
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": 11.615449250978989, "std_reward": 80.51189109258232, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-18T19:13:09.066736"}
|