Commit
·
df6265d
1
Parent(s):
b5f98fc
Push agent to the Hub
Browse files- README.md +3 -3
- logs/events.out.tfevents.1696597990.Anderss-MacBook-Pro-4.local.44255.0 +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 |
---
|
|
@@ -45,7 +45,7 @@ model-index:
|
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.999
|
| 47 |
'gae_lambda': 0.95
|
| 48 |
-
'num_minibatches':
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
|
@@ -56,6 +56,6 @@ model-index:
|
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'anders0204/ppo-LunarLander-v2'
|
| 58 |
'batch_size': 4096
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -150.78 +/- 57.81
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.999
|
| 47 |
'gae_lambda': 0.95
|
| 48 |
+
'num_minibatches': 16
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
|
|
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'anders0204/ppo-LunarLander-v2'
|
| 58 |
'batch_size': 4096
|
| 59 |
+
'minibatch_size': 256}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1696597990.Anderss-MacBook-Pro-4.local.44255.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ef1c8f1d923244105037c4f533a5ffd4210a1f3f659b55ecd4c1c277016978c
|
| 3 |
+
size 10413
|
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 sha256:61b93f78d3afbfccd16f39c5e9e5ae105ad9da06e5131c6c02ec3574b151261d
|
| 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": -150.78124932505312, "std_reward": 57.811873305553064, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-06T15:13:24.372793"}
|