Hugging Face's logo

gputrain
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
gputrain commited on
Commit
b979147
•
1 Parent(s): 0e97464

Initial commit

Browse files
Files changed (10) hide show
  1. README.md +4 -4
  2. args.yml +1 -1
  3. config.yml +3 -3
  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. 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: 404.50 +/- 117.70
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -67,16 +67,16 @@ OrderedDict([('batch_size', 64),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
- ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 5e-05),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
79
- ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
82
 
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 892.50 +/- 319.89
20
  name: mean_reward
21
  verified: false
22
  ---
 
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.025),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 5e-05),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 5000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
79
+ ('train_freq', 8),
80
  ('normalize', False)])
81
  ```
82
 
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1907036238
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 936922426
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -8,7 +8,7 @@
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
- - 0.1
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
@@ -26,4 +26,4 @@
26
  - - target_update_interval
27
  - 1000
28
  - - train_freq
29
- - 4
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.025
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 5000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
26
  - - target_update_interval
27
  - 1000
28
  - - train_freq
29
+ - 8
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b196bfa3210fe9cbf9cd70c504115b1b44f3c77fd863c206d69c6041541d73d
3
- size 27220132
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bfa7554a104919748bbc4e8a9c585f258321435e58400da42ce07530b7f06d2
3
+ size 27220135
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 sha256:7cbce9da93e2574165ec066c6317478d6a839d6973f5e1ee740087849951ace2
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d44299be953bee0c1fbf60b2e477e9e390347966b1d30e88c0dcee941b778a0
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2db2fb14b83acb105a80637a9bafcf09cb5539bce14eeb4b6c6dad5d25884173
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427df44803f3511f6f82564dc50582baf80dd1b21db9cffdf64a529fa601ca3e
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21d8e2b0580e1635589c8c5ec9780a36b58f3047263b32991eddc4848142195d
3
- size 254138
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbb081d4f8d2f4515e6f7914078092addc37c3b0988ff8c9c3ceae5b81cab39
3
+ size 203478
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 404.5, "std_reward": 117.69558190518453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-03T19:43:39.849144"}
 
1
+ {"mean_reward": 892.5, "std_reward": 319.8925600885397, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-04T01:26:38.285569"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b39ef5d02ad5b05bb11d4d5be2e6ab48153e17ca98e62f5192dc0b2d83165e7
3
- size 41253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf129e0d47d1432de710f1dc90d9f06b94a4910f008e1ffd0e747ed8b6701c9
3
+ size 161417