Push agent to the Hub
Browse files- README.md +6 -6
- logs/events.out.tfevents.1742287527.f880cbbbbdee.29118.0 +3 -0
- model.pt +1 -1
- replay.mp4 +2 -2
- 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 |
---
|
@@ -38,7 +38,7 @@ model-index:
|
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 500000
|
41 |
-
'learning_rate': 0.
|
42 |
'num_envs': 4
|
43 |
'num_steps': 128
|
44 |
'anneal_lr': True
|
@@ -48,11 +48,11 @@ model-index:
|
|
48 |
'num_minibatches': 4
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
51 |
-
'clip_coef':
|
52 |
'clip_vloss': True
|
53 |
-
'ent_coef': 0.
|
54 |
-
'vf_coef': 0.
|
55 |
-
'max_grad_norm': 0.
|
56 |
'target_kl': None
|
57 |
'repo_id': 'AGuzhvenko/ppo-CartPole-v1'
|
58 |
'batch_size': 512
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: 20.32 +/- 79.21
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
'total_timesteps': 500000
|
41 |
+
'learning_rate': 0.00025
|
42 |
'num_envs': 4
|
43 |
'num_steps': 128
|
44 |
'anneal_lr': True
|
|
|
48 |
'num_minibatches': 4
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
51 |
+
'clip_coef': 0.2
|
52 |
'clip_vloss': True
|
53 |
+
'ent_coef': 0.01
|
54 |
+
'vf_coef': 0.5
|
55 |
+
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'AGuzhvenko/ppo-CartPole-v1'
|
58 |
'batch_size': 512
|
logs/events.out.tfevents.1742287527.f880cbbbbdee.29118.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76136e99e9e9b15d6e979139e1151372d0bffe2993fe357243f598c702be89fa
|
3 |
+
size 675364
|
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:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
|
3 |
size 43026
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db130d77de94c2497f99ecc0fffa11efe2dbda6e4b6a78109133aa0debc9028a
|
3 |
+
size 166108
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"env_id": "LunarLander-v2", "mean_reward":
|
|
|
1 |
+
{"env_id": "LunarLander-v2", "mean_reward": 20.31899960425885, "std_reward": 79.21136278854874, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-18T09:00:36.705345"}
|