Hugging Face's logo

mnavas
/
spaceinv-1

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
María Navas Loro commited on
Commit
de1354f
·
1 Parent(s): 2ca498e

Initial commit

Browse files
Files changed (10) 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.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: 274.50 +/- 31.50
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']),
@@ -67,7 +67,7 @@ OrderedDict([('batch_size', 32),
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
69
  ('learning_starts', 100000),
70
- ('n_timesteps', 100000.0),
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: 484.50 +/- 189.89
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']),
 
67
  ('gradient_steps', 1),
68
  ('learning_rate', 0.0001),
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
- - 1009426013
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 2582964334
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
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
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
 
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 sha256:24697c5b89e7a63dcae20ff474c2444b12ea07397aff2660f09cc3ec0742ba6e
3
- size 13719733
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068d975e2c0ebceb647074bcc889a425e210e1ae7351fad8baf5e5ad69734471
3
+ size 27224794
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:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e5c2564023dd54bd17f7cf2ddb5e1d02dde30219bb3d18df82625a66e2dddc6
3
+ size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b6c1cb29e67c68e2015981fc439a43ee4d7f75d81ff65b1cab6c4b7a9274e2a
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac756b6f4fbffb222f837eefcb13abc0897660c02b6210e90b58375f302d06e5
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e13a11a839fea521ecfd34a27ae00521e04cfb8dd63fb3e005e2d701b498e2b
3
- size 261744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbef6a5c7add83ade35ab14d504bf32ea8eed94eeb3fbce3267fda6f2ffe4afd
3
+ size 195104
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 274.5, "std_reward": 31.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-23T18:33:18.643991"}
 
1
+ {"mean_reward": 484.5, "std_reward": 189.88746667434373, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-23T19:50:55.848344"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36ee3e3d9e94d1dedd6ce724ef4eccf6c501ac36247c58377ee1d246fb59ba51
3
- size 5773
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95c635a389a19905ca96c1b27f6de504ca20a6e79290c62b3e8bb8af6c92393
3
+ size 39815