Push agent to the Hub
Browse files- README.md +5 -5
- logs/events.out.tfevents.1677509747.5a35922b4c53.17063.0 +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 |
---
|
@@ -38,9 +38,9 @@ model-index:
|
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 100000
|
41 |
-
'learning_rate':
|
42 |
'num_envs': 4
|
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': 'akoshel/ppo-LunarLander-v2'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -154.41 +/- 72.85
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 100000
|
41 |
+
'learning_rate': 5e-05
|
42 |
'num_envs': 4
|
43 |
+
'num_steps': 1024
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'akoshel/ppo-LunarLander-v2'
|
58 |
+
'batch_size': 4096
|
59 |
+
'minibatch_size': 1024}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1677509747.5a35922b4c53.17063.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cef394e5684f64defc1dc791e47b9ce5e36abbf1a443eb0c311c8fe7771048ed
|
3 |
+
size 141877
|
model.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42817
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:351264ed5c5ef0a087db4cd76fdfee9938bbbfd178b04f64c659cf9c12746a9b
|
3 |
size 42817
|
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": -154.41380246758848, "std_reward": 72.84990333610577, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T14:56:56.131571"}
|