Hugging Face's logo

Krish2005tech2
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
Krish2005tech2 commited on
Commit
d451dbc
·
verified ·
1 Parent(s): e4714c4

Initial commit

Browse files
Files changed (9) 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 +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
  ---
@@ -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: 682.00 +/- 171.93
20
  name: mean_reward
21
  verified: false
22
  ---
 
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),
args.yml CHANGED
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 2826731881
60
  - - storage
61
  - null
62
  - - study_name
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 3876130109
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
+ - 1000000.0
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:a78b4f7d89180644cdc9370a25905e53fc4bc20dc913766f8f89b5ed0c9eb701
3
- size 13714544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2dcced3e2f7c3c5d6c5903fa66f1b140f88ee8f9f2a17b4673e219f58be5256
3
+ size 27219601
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 sha256:43cd8771f91ffb88580ebfd216a97461f7a69acd97a7b7daa16866d30baa0673
3
- size 1517
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db655f3c199e6bc1514240696e9ebbe0b82f05a7313c438d2510f357a33a6478
3
+ size 13506569
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:260b0eb0d2be59da28b045b6c35691ed103525445423506909b501353e4b51aa
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5009df02a339e1137f1d39c95ec39c074265934ab04f7970fa98c0107370fd0d
3
  size 13505767
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 329.0, "std_reward": 157.96835126062436, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-28T14:50:18.158469"}
 
1
+ {"mean_reward": 682.0, "std_reward": 171.93312653470826, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-28T15:59:17.587327"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a1f7a6c66195e9ba37f6b9f12250b34911d9410c1cb2021bc21cc123b65df1f
3
- size 5716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c051dc0ada97b6614e7a014eb2d2ee67246ca567ae8aa327bd72f0c2f40d7310
3
+ size 35803