Hugging Face's logo

guneomkar
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
guneomkar commited on
Commit
896992a
·
verified ·
1 Parent(s): e89351b

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +3 -3
  2. args.yml +1 -1
  3. config.yml +2 -2
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. results.json +1 -1
  9. 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: 329.00 +/- 157.97
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,8 +72,8 @@ OrderedDict([('batch_size', 32),
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
- ('learning_starts', 100000),
76
- ('n_timesteps', 1000.0),
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: 117.00 +/- 153.53
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('frame_stack', 4),
73
  ('gradient_steps', 1),
74
  ('learning_rate', 0.0001),
75
+ ('learning_starts', 1000),
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
- - 1951935396
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3414669061
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -16,9 +16,9 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 100000
20
  - - n_timesteps
21
- - 1000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 1000
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 sha256:05b9ee64086bee6764c346004ccdebf79edc481e115ed2c50b15b4bd79e4b335
3
- size 13712530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647ff33a8baf8e5346abc37f19e3f8243aa69f47d479989011a01a1a8de404db
3
+ size 27218123
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 sha256:215ea7d8898faa9284464c7109532cf36390d330fccab8d77eeba20628a32876
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1d8a68174a38dc50f20c75ae7f2c3adfe1056aae02fee2380aa182ba8ed1fb
3
+ size 13506172
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c011c0bba85048999d88e58c1ac2f5a65be5d1c3e506e8efd08b83d42020bb0
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15df3149473ec700b92b7dc2d02f391f156691cc31804a9c7ab6fd9c69d31fe
3
  size 13505370
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-23T01:16:14.637433"}
 
1
+ {"mean_reward": 117.0, "std_reward": 153.52849898308781, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-23T01:20:30.989806"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2da105faf6cf68f46e965877ef1d198d977e08a36a8fd39da5b18831cc3f6ec
3
- size 245
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f942d01bfeed1316c8a92ea7eb944b337c2994e1ba72f5d940e7b3ca0e227c
3
+ size 524