Hugging Face's logo

Nikhil058
/
dqn_SpaceInvadersNoFrameskip-v4_1

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
Nikhil058 commited on
Commit
8348222
·
1 Parent(s): e6720cb

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 +2 -2
  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: 270.00 +/- 0.00
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -71,11 +71,11 @@ OrderedDict([('batch_size', 32),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
- ('learning_starts', 1000),
75
- ('n_timesteps', 1e-05),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
- ('target_update_interval', 100),
79
  ('train_freq', 4),
80
  ('normalize', False)])
81
  ```
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 523.50 +/- 115.13
20
  name: mean_reward
21
  verified: false
22
  ---
 
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
+ ('learning_starts', 100),
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
  ```
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 68290942
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1571342660
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -16,14 +16,14 @@
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
- - 1000
20
  - - n_timesteps
21
- - 1.0e-05
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
- - 100
28
  - - train_freq
29
  - 4
 
16
  - - learning_rate
17
  - 0.0001
18
  - - learning_starts
19
+ - 100
20
  - - n_timesteps
21
+ - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
25
  - CnnPolicy
26
  - - target_update_interval
27
+ - 1000
28
  - - train_freq
29
  - 4
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb70a312b097503ac41dcc67c4f9a299a27f22b48a0ed10752a851f883a86024
3
- size 13672955
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25aaa0afa6da9640cffc588ebf11a6fb6b2f17e5baac6c273b487af0fac62663
3
+ size 27220129
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:e3fc84919e676e2bdcaa04814c7dfa2b7625d8d53a818418c6db25771364db93
3
- size 1120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a456080c2648b7235075080a5e027d52a2c14edf7d9c8f24fbb2476e7606ec34
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:bf8067041c1110b81bba541fb54b722bb178ba2f1cd11c53bd6b1c84f22dfc87
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bcc330989e90152c850d9b3f1cc3467bee31f17f89398a94da0c0bcc7155977
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a36e3fe8961766ab38dda9750258eb43e0a871a98ac02992ffa42fdd8756b529
3
- size 247208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dbd9a144ead1a759d3e6654b4675527c76d5b372c7cab60683a317b9ef2bb9a
3
+ size 220314
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 270.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-27T19:03:53.662793"}
 
1
+ {"mean_reward": 523.5, "std_reward": 115.1314466164653, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-27T21:28:29.812608"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0529594be53217d2366c8c5b60229a2df9dae59f7c72ae3c14562ec082824372
3
- size 205
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa5e24435df4066bb9022206cf4e760b90cd7d3a91bc65c1dfb0c6299428f629
3
+ size 35531