Push agent to the Hub
Browse files- README.md +3 -3
- 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 |
---
|
@@ -31,14 +31,14 @@ model-index:
|
|
31 |
{'exp_name': 'ppo'
|
32 |
'seed': 1
|
33 |
'env_id': 'LunarLander-v2'
|
34 |
-
'total_timesteps':
|
35 |
'target_kl': None
|
36 |
'max_grad_norm': 0.5
|
37 |
'vf_coef': 0.5
|
38 |
'ent_coef': 0.01
|
39 |
'clip_coef': 0.2
|
40 |
'clip_vloss': True
|
41 |
-
'num_steps':
|
42 |
'learning_rate': 0.00025
|
43 |
'gae': True
|
44 |
'gamma': 0.99
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -104.18 +/- 83.56
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
31 |
{'exp_name': 'ppo'
|
32 |
'seed': 1
|
33 |
'env_id': 'LunarLander-v2'
|
34 |
+
'total_timesteps': 100000
|
35 |
'target_kl': None
|
36 |
'max_grad_norm': 0.5
|
37 |
'vf_coef': 0.5
|
38 |
'ent_coef': 0.01
|
39 |
'clip_coef': 0.2
|
40 |
'clip_vloss': True
|
41 |
+
'num_steps': 128
|
42 |
'learning_rate': 0.00025
|
43 |
'gae': True
|
44 |
'gamma': 0.99
|
model.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42597
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4f0bc0f1503a07837560199df54821ffc0e0a4e66cafdfeaa50612bad3296e9
|
3 |
size 42597
|
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": -104.1814593575411, "std_reward": 83.55580372276808, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-27T16:19:24.156573"}
|