FredericProtat
commited on
Commit
•
59c52d2
1
Parent(s):
202cf62
Push agent to the Hub
Browse files- README.md +5 -5
- logs/events.out.tfevents.1694597208.422f4b7e0f84.7583.0 +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 |
---
|
@@ -41,10 +41,10 @@ model-index:
|
|
41 |
'capture_video': False
|
42 |
'env_id': 'LunarLander-v2'
|
43 |
'num_envs': 4
|
44 |
-
'num_steps':
|
45 |
'anneal_lr': True
|
46 |
'gae': True
|
47 |
-
'gamma': 0.
|
48 |
'gae_lambda': 0.98
|
49 |
'num_minibatches': 4
|
50 |
'update_epochs': 4
|
@@ -56,7 +56,7 @@ model-index:
|
|
56 |
'max_grad_norm': 0.5
|
57 |
'target_kl': None
|
58 |
'repo_id': 'FredericProtat/ppo-LunarLander-v2'
|
59 |
-
'batch_size':
|
60 |
-
'minibatch_size':
|
61 |
```
|
62 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -136.70 +/- 64.03
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
41 |
'capture_video': False
|
42 |
'env_id': 'LunarLander-v2'
|
43 |
'num_envs': 4
|
44 |
+
'num_steps': 1024
|
45 |
'anneal_lr': True
|
46 |
'gae': True
|
47 |
+
'gamma': 0.999
|
48 |
'gae_lambda': 0.98
|
49 |
'num_minibatches': 4
|
50 |
'update_epochs': 4
|
|
|
56 |
'max_grad_norm': 0.5
|
57 |
'target_kl': None
|
58 |
'repo_id': 'FredericProtat/ppo-LunarLander-v2'
|
59 |
+
'batch_size': 4096
|
60 |
+
'minibatch_size': 1024}
|
61 |
```
|
62 |
|
logs/events.out.tfevents.1694597208.422f4b7e0f84.7583.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62d13365ccaf30585dc28f30351c3d3b5e3c92db0e8a77f3234216e13d088296
|
3 |
+
size 141109
|
model.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 42469
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ebf3465c38ec32051261e720f626890cc85ca8688e353209b67003d4a9114ce
|
3 |
size 42469
|
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": -136.70251694105684, "std_reward": 64.02571409714388, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:27:41.162511"}
|