Hugging Face's logo

winkin119
/
A3C-CartPoleV1

Reinforcement Learning
TensorBoard
PyTorch
CartPole-v1
a3c with gae
custom-implementation
policy-gradient
a3c
gae
Eval Results (legacy)
Model card Files
xet
 Metrics Community
winkin119 commited on
Commit
ebc82b9
·
verified ·
1 Parent(s): 699eb0c

test hub

Browse files
Files changed (27) hide show
  1. README.md +35 -0
  2. a3c.pth +3 -0
  3. eval_result.json +1 -0
  4. params.json +48 -0
  5. replay.mp4 +0 -0
  6. tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6100.0 +3 -0
  7. tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6101.0 +3 -0
  8. tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6102.0 +3 -0
  9. tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6103.0 +3 -0
  10. tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6104.0 +3 -0
  11. tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6105.0 +3 -0
  12. tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6368.0 +3 -0
  13. tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6369.0 +3 -0
  14. tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6370.0 +3 -0
  15. tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6371.0 +3 -0
  16. tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6372.0 +3 -0
  17. tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6373.0 +3 -0
  18. video/rl-video-episode-0.mp4 +0 -0
  19. video/rl-video-episode-10.mp4 +0 -0
  20. video/rl-video-episode-15.mp4 +0 -0
  21. video/rl-video-episode-20.mp4 +0 -0
  22. video/rl-video-episode-25.mp4 +0 -0
  23. video/rl-video-episode-30.mp4 +0 -0
  24. video/rl-video-episode-35.mp4 +0 -0
  25. video/rl-video-episode-40.mp4 +0 -0
  26. video/rl-video-episode-45.mp4 +0 -0
  27. video/rl-video-episode-5.mp4 +0 -0
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ env_name: CartPole-v1
3
+ tags:
4
+ - CartPole-v1
5
+ - a3c with gae
6
+ - reinforcement-learning
7
+ - custom-implementation
8
+ - A3C
9
+ - GAE
10
+ model-index:
11
+ - name: A3C-CartPoleV1
12
+ results:
13
+ - task:
14
+ type: reinforcement-learning
15
+ name: reinforcement-learning
16
+ dataset:
17
+ name: CartPole-v1
18
+ type: CartPole-v1
19
+ metrics:
20
+ - type: mean_reward
21
+ value: 496.28 +/- 13.12
22
+ name: mean_reward
23
+ verified: false
24
+ ---
25
+
26
+ # **A3C with GAE** Agent playing **CartPole-v1**
27
+ This is a trained model of a **A3C with GAE** agent playing **CartPole-v1**.
28
+
29
+ ## Usage
30
+
31
+ model = load_from_hub(repo_id="winkin119/A3C-CartPoleV1", filename="a3c.pth")
32
+
33
+
34
+ env = gym.make("CartPole-v1")
35
+ ...
a3c.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:533f010c65a084013e402bb66e1e016d5cc311137cb731ab199f5ce0dab4949e
3
+ size 26231
eval_result.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 496.28, "std_reward": 13.122560725712036, "datetime": "2025-07-22 23:13:59", "train_duration_min": "0.28"}
params.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "env_config": {
3
+ "env_id": "CartPole-v1",
4
+ "env_kwargs": {},
5
+ "max_steps": null,
6
+ "use_image": false,
7
+ "vector_env_num": 2,
8
+ "use_multi_processing": false,
9
+ "image_shape": null,
10
+ "frame_stack": 1,
11
+ "frame_skip": 1,
12
+ "training_render_mode": null
13
+ },
14
+ "device": "cpu",
15
+ "learning_rate": 0.0001,
16
+ "gamma": 0.99,
17
+ "checkpoint_pathname": "",
18
+ "eval_episodes": 50,
19
+ "eval_random_seed": 42,
20
+ "eval_video_num": 10,
21
+ "total_steps": 25000,
22
+ "rollout_len": 32,
23
+ "gae_lambda_or_n_step": 0.97,
24
+ "entropy_coef": {
25
+ "_type": "LinearSchedule",
26
+ "_module": "practice.utils_for_coding.scheduler_utils",
27
+ "start_e": 0.2,
28
+ "end_e": 0.1,
29
+ "duration": 200
30
+ },
31
+ "value_loss_coef": 0.02,
32
+ "grad_acc": 1,
33
+ "max_grad_norm": 0.5,
34
+ "critic_lr": 5e-05,
35
+ "critic_lr_gamma": 0.95,
36
+ "normalize_returns": true,
37
+ "hidden_size": 64,
38
+ "num_workers": 6,
39
+ "env_wrappers": [
40
+ "CartPoleEnv",
41
+ "PassiveEnvChecker",
42
+ "OrderEnforcing",
43
+ "TimeLimit",
44
+ "CastObsFloat32Wrapper",
45
+ "RecordEpisodeStatistics",
46
+ "Autoreset"
47
+ ]
48
+ }
replay.mp4 ADDED
Binary file (27.9 kB). View file
 
tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6100.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f8b1c29e45520be58b5818462e2ce7d5cab1acec664e7215a5dfc3d84489349
3
+ size 183154
tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6101.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5480455b02db7836f3d54930a20be4f1556f67a98bf9250c4b621d43709cc91
3
+ size 181026
tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6102.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f44d77764872f43151798c3a28c3e9231ef4d523b0f7fb8ea0b6309fa70f49
3
+ size 182298
tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6103.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca090b8e85418389f839e6e63731ea5f3d26f90060e19554832dec0327251cd3
3
+ size 182720
tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6104.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5c93c00e614c351f61df723ff435f4b6e6a08b71e5ba8d3952204112f859985
3
+ size 180706
tensorboard/events.out.tfevents.1753197165.winkindeMacBook-Air.local.6105.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f10c89e216f0705b261d07eca5f5ffdb1d46ca7b080ed16c5b67581642f6989
3
+ size 183250
tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6368.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba47fbb1be53cf84e1d6fbbff340d14303df21d8573a31f25e224117312c9cbf
3
+ size 176996
tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6369.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a926f46fd4a57897a984381e6b1e379a751aa5c19474f8aa6cc0487c5f7224b
3
+ size 177844
tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6370.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f5b66bfcee2ca6f8b22171bb84719863f233438f0421a16c8012972596ff64
3
+ size 179328
tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6371.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304193c55f1b552282730d42b3f36562140005a889584d0dcc11af696473dc51
3
+ size 175618
tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d171c43be76de6723d816ca0585b44385a008b934a99504b4fecd971bb656066
3
+ size 174662
tensorboard/events.out.tfevents.1753197215.winkindeMacBook-Air.local.6373.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f91f10c551952019de054fc685f8b1f47de79150bbf8a357c89adf0c49c1f4
3
+ size 176782
video/rl-video-episode-0.mp4 ADDED
Binary file (27.1 kB). View file
 
video/rl-video-episode-10.mp4 ADDED
Binary file (29.3 kB). View file
 
video/rl-video-episode-15.mp4 ADDED
Binary file (33 kB). View file
 
video/rl-video-episode-20.mp4 ADDED
Binary file (29.7 kB). View file
 
video/rl-video-episode-25.mp4 ADDED
Binary file (30 kB). View file
 
video/rl-video-episode-30.mp4 ADDED
Binary file (27.9 kB). View file
 
video/rl-video-episode-35.mp4 ADDED
Binary file (28.3 kB). View file
 
video/rl-video-episode-40.mp4 ADDED
Binary file (31.9 kB). View file
 
video/rl-video-episode-45.mp4 ADDED
Binary file (28.3 kB). View file
 
video/rl-video-episode-5.mp4 ADDED
Binary file (29.5 kB). View file