kavindumit commited on
Commit
a8a092a
·
verified ·
1 Parent(s): e47350e

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -25,7 +25,6 @@
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
 
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
  *.tflite filter=lfs diff=lfs merge=lfs -text
29
  *.tgz filter=lfs diff=lfs merge=lfs -text
30
  *.wasm filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 713.50 +/- 96.83
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -35,7 +35,6 @@ with hyperparameter optimization and pre-trained agents included.
35
  RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
  SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
  SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
38
- SBX (SB3 + Jax): https://github.com/araffin/sbx
39
 
40
  Install the RL Zoo (with SB3 and SB3-Contrib):
41
  ```bash
@@ -44,13 +43,13 @@ pip install rl_zoo3
44
 
45
  ```
46
  # Download model and save it into the logs/ folder
47
- python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Kolosok -f logs/
48
  python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
49
  ```
50
 
51
  If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
52
  ```
53
- python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Kolosok -f logs/
54
  python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
55
  ```
56
 
@@ -58,7 +57,7 @@ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
58
  ```
59
  python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
60
  # Upload the model and generate video (when possible)
61
- python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Kolosok
62
  ```
63
 
64
  ## Hyperparameters
@@ -73,15 +72,10 @@ OrderedDict([('batch_size', 32),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 1000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
80
  ('train_freq', 4),
81
  ('normalize', False)])
82
  ```
83
-
84
- # Environment Arguments
85
- ```python
86
- {'render_mode': 'rgb_array'}
87
- ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 889.50 +/- 289.46
20
  name: mean_reward
21
  verified: false
22
  ---
 
35
  RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
  SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
  SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
 
38
 
39
  Install the RL Zoo (with SB3 and SB3-Contrib):
40
  ```bash
 
43
 
44
  ```
45
  # Download model and save it into the logs/ folder
46
+ python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga HaiderAUT -f logs/
47
  python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
48
  ```
49
 
50
  If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
51
  ```
52
+ python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga HaiderAUT -f logs/
53
  python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
54
  ```
55
 
 
57
  ```
58
  python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
59
  # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga HaiderAUT
61
  ```
62
 
63
  ## Hyperparameters
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
 
 
 
 
 
args.yml CHANGED
@@ -2,15 +2,13 @@
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
- - dqn.yml
6
  - - device
7
  - auto
8
  - - env
9
  - SpaceInvadersNoFrameskip-v4
10
  - - env_kwargs
11
  - null
12
- - - eval_env_kwargs
13
- - null
14
  - - eval_episodes
15
  - 5
16
  - - eval_freq
@@ -56,7 +54,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 381900577
60
  - - storage
61
  - null
62
  - - study_name
@@ -67,8 +65,6 @@
67
  - false
68
  - - trained_agent
69
  - ''
70
- - - trial_id
71
- - null
72
  - - truncate_last_trajectory
73
  - true
74
  - - uuid
@@ -83,3 +79,5 @@
83
  - sb3
84
  - - wandb_tags
85
  - []
 
 
 
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
+ - null
6
  - - device
7
  - auto
8
  - - env
9
  - SpaceInvadersNoFrameskip-v4
10
  - - env_kwargs
11
  - null
 
 
12
  - - eval_episodes
13
  - 5
14
  - - eval_freq
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2243915477
58
  - - storage
59
  - null
60
  - - study_name
 
65
  - false
66
  - - trained_agent
67
  - ''
 
 
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
 
79
  - sb3
80
  - - wandb_tags
81
  - []
82
+ - - yaml_file
83
+ - null
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f19ccbc80cb66b553a31d2a9002979b6a26b042528dd4c29fbe45c099a632b7d
3
- size 27219597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c706d585845776535bada5f6b6c6753dfb610b1bc3d15bb1c13e967b1f00bd0c
3
+ size 27225013
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.7.0
 
1
+ 1.8.0a2
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0af50457e5905a4c41e80a1f79a6714359b5a6a8928a5473cbeef81e03dec23c
3
- size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e47ab09ab431c14712f926a60c2bc21578b6e870c7ac2074cd22997ff9e2fd6
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84dc331d0e18ccb562ff95fc23280a9bb6e7398b33cb0cc551bb53d1fd073dc5
3
- size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bd94d828fe365b570bcccf70f03facd27714afdc63d90a3ebe8de184491ebb2
3
+ size 13504937
dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07c7431cf6005e7d8f367d79e995f63e2f9b981a37e3437b795d058f9af4308b
3
- size 1261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,7 @@
1
- - OS: Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct 2 10:42:05 UTC 2025
2
- - Python: 3.12.12
3
- - Stable-Baselines3: 2.7.0
4
- - PyTorch: 2.8.0+cu126
5
  - GPU Enabled: True
6
- - Numpy: 2.0.2
7
- - Cloudpickle: 3.1.1
8
- - Gymnasium: 1.2.1
9
- - OpenAI Gym: 0.25.2
 
1
+ - OS: Linux-5.10.16.3-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Apr 2 22:23:49 UTC 2021
2
+ - Python: 3.10.9
3
+ - Stable-Baselines3: 1.8.0a2
4
+ - PyTorch: 1.13.1+cu117
5
  - GPU Enabled: True
6
+ - Numpy: 1.23.5
7
+ - Gym: 0.21.0
 
 
env_kwargs.yml CHANGED
@@ -1 +1 @@
1
- render_mode: rgb_array
 
1
+ {}
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21ccb65236a5ee88da2137e25b6cc987c96a8e733ede307a5b0a966ec0506b2d
3
+ size 171038
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 713.5, "std_reward": 96.82587464102764, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-10-15T11:24:26.433149"}
 
1
+ {"mean_reward": 889.5, "std_reward": 289.4602736128051, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-01T11:15:20.817406"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9cff95733983b1ee63368d93b9973880c7c408c0fc4bf47eadc8f6d95c6e3a1
3
- size 36876
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420fa535f2be84f821d3163b122aada33786f8068ec431d781c2d446f06568b5
3
+ size 270929