Hugging Face's logo

FadySamy
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
FadySamy commited on
Commit
849cee9
·
1 Parent(s): ed3d2fe

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.pth +1 -1
  7. replay.mp4 +2 -2
  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: 136.00 +/- 58.00
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,7 +62,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
62
 
63
  ## Hyperparameters
64
  ```python
65
- OrderedDict([('batch_size', 128),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 128),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 268.50 +/- 78.17
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 4248293170
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 656077943
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 128
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 64
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 100000.0
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 sha256:027dee5e25f64a2fe704481f8566a8d364ec2a8c41952942945fcb41383cc9d0
3
- size 13711827
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f724ba192b8fa70abd8dce1059644c3cfbb7463e01a509f442b9aa670c52b8
3
+ size 13714993
dqn-SpaceInvadersNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:584df028e2a60fa1ae24512d7e1cb08ddc65782f169221492ead46130ac44b48
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e1515539fd751329ed0f9c212ce661932959b932d77c3a41018cc0212c4179b
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8418d0f523dfdd4cef4d8bc44806976b44912d68c308b2afd2cdd1f357f2362d
3
- size 258913
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a799ac9657faeb813344ec56ae265d381f35a430091e2c90337e271719a9db
3
+ size 278674
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 136.0, "std_reward": 58.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-04T16:56:17.129306"}
 
1
+ {"mean_reward": 268.5, "std_reward": 78.16808811785025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-12-04T17:05:23.611150"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0222c47a85cb17b7fa5c63c640016fd8ff6ecaf042f317c51f2db640158ffe28
3
- size 696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96931bef3eeae128edb35c4463a585c54e0155807c6cb9e50833ba64d7f1b8e1
3
+ size 5874