Hugging Face's logo

RamonAnkersmit
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
RamonAnkersmit commited on
Commit
3d59e7b
·
1 Parent(s): cc30ea3

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: 266.00 +/- 95.39
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -57,7 +57,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
57
 
58
  ## Hyperparameters
59
  ```python
60
- OrderedDict([('batch_size', 32),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -65,9 +65,9 @@ OrderedDict([('batch_size', 32),
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
- ('learning_rate', 1e-05),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 2000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 374.00 +/- 214.89
20
  name: mean_reward
21
  verified: false
22
  ---
 
57
 
58
  ## Hyperparameters
59
  ```python
60
+ OrderedDict([('batch_size', 16),
61
  ('buffer_size', 100000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
65
  ('exploration_fraction', 0.1),
66
  ('frame_stack', 4),
67
  ('gradient_steps', 1),
68
+ ('learning_rate', 0.001),
69
  ('learning_starts', 100000),
70
+ ('n_timesteps', 1000000.0),
71
  ('optimize_memory_usage', False),
72
  ('policy', 'CnnPolicy'),
73
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 2102923977
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1069349440
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
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 1.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 2000000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 16
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.001
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:bf6b16fe686eaf6174abb0e83cc03c392536b6a97402412b1412de3b0c101cb3
3
- size 27224789
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ceaa737a7114cbb5f1191c306bbed863daa9ae826b938d5a5b3846cb59f4638
3
+ size 27224788
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:df24b374d3f023a2dd793cab5521ea96cbbe3ed37cd8c3f2e7c4a5a1414df2fc
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375b860e110b7be2f9da38da3f0fe7bcc503a5d007cf2e7ae753dcaf3cf8ec9f
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45c5b23804077093208b0ac3b2622fef66925fff1b18005e0b26f29a0772c075
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3b4f8a1ec2a36d84f01ff7b9e0b6fbfb52154b65ccf7b0fcc1c0be80c200e3
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcba93444cb8e9de953d473271591957ac91266c2739fde4d989e1a09ef64150
3
- size 261557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b231c3e33922a65189db4066e7414df0b5a66d5fa35017253dc63dd0d43b457
3
+ size 233415
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 266.0, "std_reward": 95.38867857350787, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-19T20:54:21.307944"}
 
1
+ {"mean_reward": 374.0, "std_reward": 214.89299662855464, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-19T22:14:07.643212"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a172b925f04db2da91c5aaeec01990999fae740291053ccae58bba5c45e562e
3
- size 91041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25471be8f6630682b10afbad6ed662f144cdf126f6abdb4bed4cb6d88dc2fea9
3
+ size 40539