Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1676656315.257c6859eaaa.3411.0 +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': 1000000
|
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': 'bonadio/LunarLander-PPO-unit8'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: 95.89 +/- 149.49
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
40 |
'total_timesteps': 1000000
|
41 |
'learning_rate': 0.00025
|
42 |
'num_envs': 4
|
43 |
+
'num_steps': 16
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.99
|
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'bonadio/LunarLander-PPO-unit8'
|
58 |
+
'batch_size': 64
|
59 |
+
'minibatch_size': 16}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1676656315.257c6859eaaa.3411.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8081eee772069b563f4375a93bcaf0777282fea185b3e1e3fcdd58772a3677f3
|
3 |
+
size 8474942
|
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 sha256:14d3bac0df49bbd8b58023fec01736801dcdfe8bbb1844fe1b68d633b0d397ba
|
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": 95.89106759949523, "std_reward": 149.48500309822217, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T18:35:35.270675"}
|