Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1725020324.bd5e60046b14.14765.0 +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 |
---
|
@@ -40,7 +40,7 @@ model-index:
|
|
40 |
'total_timesteps': 100000
|
41 |
'learning_rate': 0.00025
|
42 |
'num_envs': 4
|
43 |
-
'num_steps':
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
@@ -55,7 +55,7 @@ model-index:
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'jarski/myppo-LunarLander-v2'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -182.66 +/- 122.63
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
40 |
'total_timesteps': 100000
|
41 |
'learning_rate': 0.00025
|
42 |
'num_envs': 4
|
43 |
+
'num_steps': 2024
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'jarski/myppo-LunarLander-v2'
|
58 |
+
'batch_size': 8096
|
59 |
+
'minibatch_size': 2024}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1725020324.bd5e60046b14.14765.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2ffaf6c3663dd477dd57657d9f8524ace8916563427abc4dda5be72dba3e18d
|
3 |
+
size 133027
|
model.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43026
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcce7cf6df678b7fa3d387538cfb7efe745b3dbcb6e76b6f620c87d49d039c06
|
3 |
size 43026
|
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": -182.66404142577463, "std_reward": 122.62986649338978, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-30T12:20:05.337138"}
|