Push agent to the Hub
Browse files- README.md +9 -9
- logs/events.out.tfevents.1700616999.ebdfe1e9c633.20131.0 +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: 91
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
@@ -37,25 +37,25 @@ model-index:
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
-
'total_timesteps':
|
41 |
'learning_rate': 0.0005
|
42 |
'num_envs': 10
|
43 |
-
'num_steps':
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
47 |
'gae_lambda': 0.95
|
48 |
-
'num_minibatches':
|
49 |
-
'update_epochs':
|
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.
|
56 |
-
'target_kl':
|
57 |
'repo_id': 'jrad98/lunar_lander_v2_unit8_part1'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: 81.91 +/- 175.33
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
+
'total_timesteps': 250000
|
41 |
'learning_rate': 0.0005
|
42 |
'num_envs': 10
|
43 |
+
'num_steps': 500
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
47 |
'gae_lambda': 0.95
|
48 |
+
'num_minibatches': 20
|
49 |
+
'update_epochs': 40
|
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': 0.2
|
56 |
+
'target_kl': 0.2
|
57 |
'repo_id': 'jrad98/lunar_lander_v2_unit8_part1'
|
58 |
+
'batch_size': 5000
|
59 |
+
'minibatch_size': 250}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1700616999.ebdfe1e9c633.20131.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:798dc36345d38508a28b5c0efea89829989b51ef026681e48f3479a45f13c032
|
3 |
+
size 101680
|
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 sha256:63791e9b2493ba7574952b393fbd76a0d0b77603c814b1a6f215f23f6246a312
|
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": 81.9146030060001, "std_reward": 175.32574673002344, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-22T01:44:58.077114"}
|