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
82a82a8
·
verified ·
1 Parent(s): d81e163

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +1 -1
  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. replay.mp4 +2 -2
  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: 544.50 +/- 181.53
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', 128),
67
- ('buffer_size', 200000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
@@ -73,7 +73,7 @@ OrderedDict([('batch_size', 128),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
- ('n_timesteps', 2000000.0),
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: 709.00 +/- 231.90
20
  name: mean_reward
21
  verified: false
22
  ---
 
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 128),
67
+ ('buffer_size', 250000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 3000000.0),
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
- - 4273190676
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 389299471
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 128
4
  - - buffer_size
5
- - 200000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 2000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
2
  - - - batch_size
3
  - 128
4
  - - buffer_size
5
+ - 250000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 3000000.0
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:df50b808fbd7a6b1a3f368d28486507ed5c49908da257110651be369a4f288ff
3
  size 27219630
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:490d4bd2578570e1615200aa6859e65253e709db946c691d0f217dbfb28cb292
3
  size 27219630
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:f5986f927cb7a671cc05a8726493003379bca18d6efa33da4fc15ba91dd0fe2c
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e11321057416703b1b9153a4beb2ea5e53e58e4136e7b308de4658d9e563bc9
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:e345ea02839a882ecf69200844a61576cf2ff76871e6ed5b9938937c9d6f7dad
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ff2b38297b6d0bb4f4675e2571e5bca48007260cd7e422778c54cc8f59c1e9
3
  size 13505767
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c33fed231aef8ef955e69d0feabc7d475953ee84c32707444c2bed30ac2407e7
3
- size 182447
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb318606d7c8ae267f0e58bb83560d916ab4b6106046e8af7968a8e74f0b3e96
3
+ size 225148
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 544.5, "std_reward": 181.52754611903947, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-23T11:43:12.071195"}
 
1
+ {"mean_reward": 709.0, "std_reward": 231.9029969620919, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-24T00:29:25.514839"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86d873854a00145226bbc1c53f7adec76b0f2b94f528c728841d159b29db4fbd
3
- size 62248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c1b4bc9744bfecff84e51b94abbe2f623b6de42e6b2b8757789a2cb23bf61f5
3
+ size 88305