Push agent to the Hub
Browse files- README.md +5 -5
- logs/events.out.tfevents.1678613643.ZZDev.137707.0 +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 |
---
|
@@ -37,15 +37,15 @@ model-index:
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
-
'total_timesteps':
|
41 |
-
'learning_rate': 5e-05
|
42 |
'num_envs': 8
|
43 |
'num_steps': 1024
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.999
|
47 |
'gae_lambda': 0.98
|
48 |
-
'num_minibatches':
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
51 |
'clip_coef': 0.2
|
@@ -56,6 +56,6 @@ model-index:
|
|
56 |
'target_kl': None
|
57 |
'repo_id': 'zzen0008/ppo-LunarLander-v2'
|
58 |
'batch_size': 8192
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: 108.08 +/- 47.93
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
37 |
'wandb_entity': None
|
38 |
'capture_video': False
|
39 |
'env_id': 'LunarLander-v2'
|
40 |
+
'total_timesteps': 2000000
|
41 |
+
'learning_rate': 2.5e-05
|
42 |
'num_envs': 8
|
43 |
'num_steps': 1024
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.999
|
47 |
'gae_lambda': 0.98
|
48 |
+
'num_minibatches': 256
|
49 |
'update_epochs': 4
|
50 |
'norm_adv': True
|
51 |
'clip_coef': 0.2
|
|
|
56 |
'target_kl': None
|
57 |
'repo_id': 'zzen0008/ppo-LunarLander-v2'
|
58 |
'batch_size': 8192
|
59 |
+
'minibatch_size': 32}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1678613643.ZZDev.137707.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e4f4df8b1c73282a971a1013daf761e6d430cca5e072a4b9ac1fb34c4389f6d
|
3 |
+
size 724420
|
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 sha256:1f57fead28cfa920ae1bac5ed27a534976016ec5205c40728fc0ae142f87c8ab
|
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": 108.07934120545636, "std_reward": 47.931577704845246, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T21:14:56.446943"}
|