Hugging Face's logo

Gonke
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
Gonke commited on
Commit
ec430eb
·
1 Parent(s): afb5247

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: 307.00 +/- 96.88
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,12 +62,12 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
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', 0.0001),
@@ -76,7 +76,7 @@ OrderedDict([('batch_size', 32),
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: 492.00 +/- 231.17
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 1024),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
+ ('exploration_fraction', 0.2),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
 
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
79
+ ('train_freq', 16),
80
  ('normalize', False)])
81
  ```
82
 
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2960645433
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3718628567
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -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
@@ -26,4 +26,4 @@
26
  - - target_update_interval
27
  - 1000
28
  - - train_freq
29
- - 4
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 1024
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
8
  - - exploration_final_eps
9
  - 0.01
10
  - - exploration_fraction
11
+ - 0.2
12
  - - frame_stack
13
  - 4
14
  - - gradient_steps
 
26
  - - target_update_interval
27
  - 1000
28
  - - train_freq
29
+ - 16
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9517cee57838dbf868805803a7c994a9f0498c0392546335b06bcc6ec08cf77e
3
- size 27220210
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38587e1862357182df3f672d421bc9d929683c929cfd0d04ca71c15f7d53e7aa
3
+ size 27220209
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 sha256:3fc4eb44eec5301521dc494b007c2b1564f05e5007f75b9c3fc12cec9728fb85
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21bb7d0fd40160ed1acdacafe8bb3d18b02a85c73d5aa16dbe978584cc68efad
3
  size 13506236
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b93b37c4cfa30dadee53db92c9ec47440682704fb9a1d78570eb6d1f454996f
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666362e7b8dfbc9ac25dfbc845305629d2236e2f4cd928afcf1984e4a1e9b360
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:160723733ad4d613ad4f68d7f6fd9ba671fef650a961827b9d7ab790d6352041
3
- size 264801
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b26748f66964e8ac2454becb6996ef3c607ed86e7cbd21b90a3bbd9e0ef318
3
+ size 263213
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 307.0, "std_reward": 96.88137075826292, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-27T21:50:36.138046"}
 
1
+ {"mean_reward": 492.0, "std_reward": 231.1730953203681, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-27T23:22:01.119481"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbc6a63d771d0908a943c5f94d6c5f38f6df8ae18c12241c20c4ea2682bd8249
3
- size 12747
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bad0395093cd87ff5e2642484274c70d36b2129e6ba159bc79c5ed3e27b45f1
3
+ size 38929