Push agent to the Hub
Browse files- README.md +5 -5
- logs/events.out.tfevents.1694792140.671b56c68840.14985.0 +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 |
---
|
|
@@ -37,14 +37,14 @@ model-index:
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
-
'total_timesteps':
|
| 41 |
-
'learning_rate': 0.
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
-
'gamma': 0.
|
| 47 |
-
'gae_lambda': 0.
|
| 48 |
'num_minibatches': 4
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: 147.26 +/- 112.06
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
+
'total_timesteps': 500000
|
| 41 |
+
'learning_rate': 0.0005
|
| 42 |
'num_envs': 4
|
| 43 |
'num_steps': 128
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
+
'gamma': 0.995
|
| 47 |
+
'gae_lambda': 0.99
|
| 48 |
'num_minibatches': 4
|
| 49 |
'update_epochs': 4
|
| 50 |
'norm_adv': True
|
logs/events.out.tfevents.1694792140.671b56c68840.14985.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b33e962a48f0cdc766106c4e84020fd07f30ed5d915b7f48b12a32dc857f0f87
|
| 3 |
+
size 716774
|
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 sha256:700d4cd6954fdbcf08c19b9e66151777c4de994f3bcea5ca07839a19425ea598
|
| 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": 147.26148487119275, "std_reward": 112.06284165649575, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-15T15:45:59.577804"}
|