Commit
•
ab0d6ea
1
Parent(s):
c1ee563
Push agent to the Hub
Browse files- README.md +3 -3
- logs/events.out.tfevents.1677779398.6c4e5c51f044.11326.0 +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 |
---
|
@@ -37,7 +37,7 @@ model-index:
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
-
'total_timesteps':
|
41 |
'learning_rate': 0.01
|
42 |
'num_envs': 4
|
43 |
'num_steps': 128
|
@@ -48,7 +48,7 @@ model-index:
|
|
48 |
'num_minibatches': 4
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
51 |
-
'clip_coef': 0.
|
52 |
'clip_vloss': True
|
53 |
'ent_coef': 0.01
|
54 |
'vf_coef': 0.5
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -156.62 +/- 68.09
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
+
'total_timesteps': 3000
|
41 |
'learning_rate': 0.01
|
42 |
'num_envs': 4
|
43 |
'num_steps': 128
|
|
|
48 |
'num_minibatches': 4
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
51 |
+
'clip_coef': 0.5
|
52 |
'clip_vloss': True
|
53 |
'ent_coef': 0.01
|
54 |
'vf_coef': 0.5
|
logs/events.out.tfevents.1677779398.6c4e5c51f044.11326.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f3085551e378c13f28f41d6cc4440768187d02ee735018f05b567d479b9218e
|
3 |
+
size 5531
|
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:abb941b53b1cd7da520924ad2e3ca5ef50ff807825cd7202e1101a9d3a5d90d2
|
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": -156.620395047975, "std_reward": 68.08605046149418, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:50:05.791331"}
|