Hugging Face's logo

cmjaramile
/
Atari_Space_Invaders

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
cmjaramile commited on
Commit
ce4dad1
·
verified ·
1 Parent(s): 1beef5f

Initial commit

Browse files
Files changed (8) 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.pth +1 -1
  7. results.json +1 -1
  8. 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: 5.00 +/- 7.07
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', 100000.0),
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: 1.50 +/- 2.29
20
  name: mean_reward
21
  verified: false
22
  ---
 
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
  ('learning_starts', 100000),
76
+ ('n_timesteps', 10000.0),
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
- - 3732197024
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 616173381
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000.0
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:b83c13235f2604ff62baab41e1345cb1518d66ec4ee3030d1a1b4dcf52605dd6
3
- size 13714525
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bbd8ef4018dba56e61a4052f8f0555b9daafb6bdacaec3169ea1f6136da9859
3
+ size 13711177
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bda11175cf06c7c36bbcda00cb44b41a83aadc86d5eb30e3b99cb4ce8c63d58
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e8a21604708c9841e95dd45a471f79805ebcdea666f771e5f8b45a4cd6585ef
3
  size 13505767
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-06-25T22:11:43.824920"}
 
1
+ {"mean_reward": 1.5, "std_reward": 2.29128784747792, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-06-26T13:19:39.168740"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:281161d8fec46a5b3f47d2ff4445c91654c706cf32729c6fc2a936b36afe3fa3
3
- size 5771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84516e9e587fb5ef446c35072b03cb86682a9a00bbb98af9a801c8d862e084b0
3
+ size 602