Push agent to the Hub
Browse files- README.md +10 -10
- logs/events.out.tfevents.1740321370.57e0e4a6823e.7707.0 +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 |
---
|
@@ -28,7 +28,7 @@ model-index:
|
|
28 |
|
29 |
# Hyperparameters
|
30 |
```python
|
31 |
-
{'exp_name': '
|
32 |
'seed': 1
|
33 |
'torch_deterministic': True
|
34 |
'cuda': True
|
@@ -38,24 +38,24 @@ model-index:
|
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 50000
|
41 |
-
'learning_rate': 0.
|
42 |
-
'num_envs':
|
43 |
-
'num_steps':
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
47 |
'gae_lambda': 0.95
|
48 |
'num_minibatches': 4
|
49 |
-
'update_epochs':
|
50 |
'norm_adv': True
|
51 |
'clip_coef': 0.2
|
52 |
'clip_vloss': True
|
53 |
-
'ent_coef': 0.
|
54 |
'vf_coef': 0.5
|
55 |
'max_grad_norm': 0.5
|
56 |
-
'target_kl':
|
57 |
'repo_id': 'Zionamsalem/LLV2'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -186.83 +/- 116.96
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
28 |
|
29 |
# Hyperparameters
|
30 |
```python
|
31 |
+
{'exp_name': 'ppo_optimized'
|
32 |
'seed': 1
|
33 |
'torch_deterministic': True
|
34 |
'cuda': True
|
|
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 50000
|
41 |
+
'learning_rate': 0.0003
|
42 |
+
'num_envs': 8
|
43 |
+
'num_steps': 256
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
47 |
'gae_lambda': 0.95
|
48 |
'num_minibatches': 4
|
49 |
+
'update_epochs': 3
|
50 |
'norm_adv': True
|
51 |
'clip_coef': 0.2
|
52 |
'clip_vloss': True
|
53 |
+
'ent_coef': 0.005
|
54 |
'vf_coef': 0.5
|
55 |
'max_grad_norm': 0.5
|
56 |
+
'target_kl': 0.015
|
57 |
'repo_id': 'Zionamsalem/LLV2'
|
58 |
+
'batch_size': 2048
|
59 |
+
'minibatch_size': 512}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1740321370.57e0e4a6823e.7707.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3944460a8db70d6a26ff5ad8bd470d755448017fee5bdc2b17b7ab0c03092015
|
3 |
+
size 74573
|
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 sha256:064b494bef98697f62ac684ad914aac568c106059e062d09ce1bd48202935b31
|
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": -186.82807786633282, "std_reward": 116.96067705206202, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-23T14:36:33.579602"}
|