Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1702921446.6563854bb69a.6085.0 +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': 50000
|
41 |
'learning_rate': 0.0005
|
42 |
'num_envs': 4
|
43 |
-
'num_steps':
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.999
|
@@ -55,7 +55,7 @@ model-index:
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'GiuliaMP/lunar-Lander-v2-PPO'
|
58 |
-
'batch_size':
|
59 |
-
'minibatch_size':
|
60 |
```
|
61 |
|
|
|
17 |
type: LunarLander-v2
|
18 |
metrics:
|
19 |
- type: mean_reward
|
20 |
+
value: -184.49 +/- 110.12
|
21 |
name: mean_reward
|
22 |
verified: false
|
23 |
---
|
|
|
40 |
'total_timesteps': 50000
|
41 |
'learning_rate': 0.0005
|
42 |
'num_envs': 4
|
43 |
+
'num_steps': 100000
|
44 |
'anneal_lr': True
|
45 |
'gae': True
|
46 |
'gamma': 0.999
|
|
|
55 |
'max_grad_norm': 0.5
|
56 |
'target_kl': None
|
57 |
'repo_id': 'GiuliaMP/lunar-Lander-v2-PPO'
|
58 |
+
'batch_size': 400000
|
59 |
+
'minibatch_size': 100000}
|
60 |
```
|
61 |
|
logs/events.out.tfevents.1702921446.6563854bb69a.6085.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44536c2519118acd8ba615c80f9270c4945f56ffe610d075f8641a74de7cc843
|
3 |
+
size 741
|
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 sha256:6924baa5dd037fce235630a196da2d3b4ab3db5b2a406adc766bdd0487a7d923
|
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": -184.49044964697777, "std_reward": 110.12274647887837, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-18T17:44:09.799863"}
|