Hugging Face's logo

hungtrab
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
hungtrab commited on
Commit
e8fc875
·
verified ·
1 Parent(s): 4f2767e

Initial commit

Browse files
Files changed (10) 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 -3
  9. results.json +1 -1
  10. 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: 383.50 +/- 114.63
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -64,7 +64,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 32),
67
- ('buffer_size', 10000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 603.50 +/- 159.83
20
  name: mean_reward
21
  verified: false
22
  ---
 
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 32),
67
+ ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2475979744
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 1969020932
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
- - 10000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
2
  - - - batch_size
3
  - 32
4
  - - buffer_size
5
+ - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8173d8c86ab4b75a765602c8eb7ed73bbe9332218a0fd6bb1185f7cc9de0b1dc
3
- size 27219608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf7683791f41e8e4b67196b524d7c88847d83a9ab7e5abcd69339610f0c953c
3
+ size 27219613
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 sha256:69922207623b62318b37632da0cd12c4a7798bafddaddcb893b98abcb436dc0e
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7144578c689819076607c715f19d1a076f40d9ee7da13136e2b2260b6ea6b90c
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:a1c9ed1d00a02805dff113061403a31c8799217f30469b951ac2e1c9ef91d7d8
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1afdd1b5e11dcdd2e86bd88ba8c77d782a6426f68ddc6c872a65ad93393849
3
  size 13505767
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,8 +1,9 @@
1
- - OS: Linux-6.8.0-78-generic-x86_64-with-glibc2.39 # 78-Ubuntu SMP PREEMPT_DYNAMIC Tue Aug 12 11:34:18 UTC 2025
2
  - Python: 3.12.11
3
  - Stable-Baselines3: 2.7.0
4
- - PyTorch: 2.8.0+cu128
5
  - GPU Enabled: True
6
- - Numpy: 2.2.6
7
  - Cloudpickle: 3.1.1
8
  - Gymnasium: 1.2.0
 
 
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
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 383.5, "std_reward": 114.63092950857548, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-25T17:40:39.037356"}
 
1
+ {"mean_reward": 603.5, "std_reward": 159.82881467370018, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-25T10:53:38.261041"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17db2402e6b6373dbd0bffe95fd80cfa6906fc2326fab55b0cf5fb1a4ec573b3
3
- size 43205
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:585403631a05877cc0e4ffe8cb8fd06c58edd73a837ffe410fa53f9821c2d077
3
+ size 37637