hugging-robot commited on
Commit
8ab9b35
1 Parent(s): 57b5db1

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. .gitattributes +10 -2
  2. README.md +8 -7
  3. model.pt +2 -2
  4. replay.mp4 +0 -0
  5. results.json +1 -1
.gitattributes CHANGED
@@ -2,27 +2,35 @@
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
4
  *.bz2 filter=lfs diff=lfs merge=lfs -text
 
5
  *.ftz filter=lfs diff=lfs merge=lfs -text
6
  *.gz filter=lfs diff=lfs merge=lfs -text
7
  *.h5 filter=lfs diff=lfs merge=lfs -text
8
  *.joblib filter=lfs diff=lfs merge=lfs -text
9
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
 
10
  *.model filter=lfs diff=lfs merge=lfs -text
11
  *.msgpack filter=lfs diff=lfs merge=lfs -text
 
 
12
  *.onnx filter=lfs diff=lfs merge=lfs -text
13
  *.ot filter=lfs diff=lfs merge=lfs -text
14
  *.parquet filter=lfs diff=lfs merge=lfs -text
15
  *.pb filter=lfs diff=lfs merge=lfs -text
 
 
16
  *.pt filter=lfs diff=lfs merge=lfs -text
17
  *.pth filter=lfs diff=lfs merge=lfs -text
18
  *.rar filter=lfs diff=lfs merge=lfs -text
 
19
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
20
  *.tar.* filter=lfs diff=lfs merge=lfs -text
 
21
  *.tflite filter=lfs diff=lfs merge=lfs -text
22
  *.tgz filter=lfs diff=lfs merge=lfs -text
23
  *.wasm filter=lfs diff=lfs merge=lfs -text
24
  *.xz filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
- *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
- *.mp4 filter=lfs diff=lfs merge=lfs -text
 
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
4
  *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
  *.ftz filter=lfs diff=lfs merge=lfs -text
7
  *.gz filter=lfs diff=lfs merge=lfs -text
8
  *.h5 filter=lfs diff=lfs merge=lfs -text
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
  *.model filter=lfs diff=lfs merge=lfs -text
13
  *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
  *.onnx filter=lfs diff=lfs merge=lfs -text
17
  *.ot filter=lfs diff=lfs merge=lfs -text
18
  *.parquet filter=lfs diff=lfs merge=lfs -text
19
  *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
  *.pt filter=lfs diff=lfs merge=lfs -text
23
  *.pth filter=lfs diff=lfs merge=lfs -text
24
  *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
  *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
  *.tflite filter=lfs diff=lfs merge=lfs -text
30
  *.tgz filter=lfs diff=lfs merge=lfs -text
31
  *.wasm filter=lfs diff=lfs merge=lfs -text
32
  *.xz filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -6,21 +6,22 @@ tags:
6
  - custom-implementation
7
  - deep-rl-class
8
  model-index:
9
- - name: Reinforce-Pixelcopter-PLE-v0
10
  results:
11
- - metrics:
12
- - type: mean_reward
13
- value: 16.20 +/- 14.18
14
- name: mean_reward
15
- task:
16
  type: reinforcement-learning
17
  name: reinforcement-learning
18
  dataset:
19
  name: Pixelcopter-PLE-v0
20
  type: Pixelcopter-PLE-v0
 
 
 
 
 
21
  ---
22
 
23
  # **Reinforce** Agent playing **Pixelcopter-PLE-v0**
24
  This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
25
- To learn to use this model and train yours check Unit 5 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit5
26
 
 
6
  - custom-implementation
7
  - deep-rl-class
8
  model-index:
9
+ - name: reinforce_PixelCopter_v1
10
  results:
11
+ - task:
 
 
 
 
12
  type: reinforcement-learning
13
  name: reinforcement-learning
14
  dataset:
15
  name: Pixelcopter-PLE-v0
16
  type: Pixelcopter-PLE-v0
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 30.40 +/- 21.93
20
+ name: mean_reward
21
+ verified: false
22
  ---
23
 
24
  # **Reinforce** Agent playing **Pixelcopter-PLE-v0**
25
  This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
26
+ To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
27
 
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d684287a1c7642a4417a696bfb9b1bb517c273ac8824ca71b986b611b90b603
3
- size 4639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2efc767dd446f6490f9fc6996bf4771199caac2c3316d4cbf8e0aecdb048501f
3
+ size 39732
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-01T13:32:43.255143"}
 
1
+ {"env_id": "Pixelcopter-PLE-v0", "mean_reward": 30.4, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-25T13:45:59.050747"}