Hugging Face's logo

debisoft
/
SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
debisoft commited on
Commit
4d6a629
·
verified ·
1 Parent(s): 2c19158

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +4 -5
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. train_eval_metrics.zip +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 558.00 +/- 62.14
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -73,7 +73,7 @@ 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),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 865.50 +/- 355.03
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 10000000.0),
77
  ('optimize_memory_usage', False),
78
  ('policy', 'CnnPolicy'),
79
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 3632756221
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2070770046
60
  - - storage
61
  - null
62
  - - study_name
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 sha256:57b3c6264f4da90c2375d9d131aa2fdcfd35bb0385bda4513142b13cb575a220
3
- size 27219613
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d6b2e4fb261ef4e92493320b9ef64e404fb53c68b501ff9a50ae2bb1b2424f
3
+ size 27219634
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:c9404bd9f07b4141ec6ed4b69aa82bcd69b65f7b970d6d61f1ffeeea2288284d
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d2402c990d15b01af2d6783cd8aa925e849a4bff8864997a65bd8f52c079a1
3
  size 13506569
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bfc92c92e3fd8a97af058840ec180003c9a847338df3f0cdcda0a93b77ce8fa
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633b4fb1a3764542d04f1e26002a9debe9e429048f4f98ba87cc7f1ec9ee908a
3
  size 13505767
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,9 +1,8 @@
1
- - OS: Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025
2
- - Python: 3.12.11
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: 1.2.0
9
- - OpenAI Gym: 0.25.2
 
1
+ - OS: Linux-6.14.0-27-generic-x86_64-with-glibc2.39 # 27~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:38:49 UTC 2
2
+ - Python: 3.12.3
3
  - Stable-Baselines3: 2.7.0
4
+ - PyTorch: 2.7.1+cu126
5
  - GPU Enabled: True
6
+ - Numpy: 2.3.2
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.2.0
 
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d02abdb9583af8434888f7daaa80f3cb2b75b5383c2589412842f03ac79a40a
3
- size 212727
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e59944a5bcfa2c2f3b169304c23acd46552a5c85224917d977374caa258134
3
+ size 194398
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 558.0, "std_reward": 62.13694553162394, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-22T02:10:21.768649"}
 
1
+ {"mean_reward": 865.5, "std_reward": 355.0313366450911, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-22T16:45:42.543971"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c038ff5b262c2d9b842c1d347c89879d2ddac8b42b1bbe4307a5892b6be3b6c3
3
- size 35515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3303e74284b8db0e785e282ea9ff6538fb5b8f54143b44d42b37b7a650a18a
3
+ size 268799