Hugging Face's logo

6001k1d
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
6001k1d commited on
Commit
1ca6e96
•
1 Parent(s): dfc4e9d

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 +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: 443.50 +/- 142.69
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', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -70,7 +70,7 @@ OrderedDict([('batch_size', 32),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 0.0005),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 579.50 +/- 324.58
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 128),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
  ('n_timesteps', 1000000.0),
76
  ('optimize_memory_usage', False),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1369869918
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 778315256
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
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0005
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 128
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80c0bff12a1b75ba0f011876d3786f822a8f863441874ab3f088cac69ce6857b
3
- size 27220208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d38a4254a458e6aa2b4139c38e8591b3770d3b8cc346328396af97016e5055
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:b3541a8b6758b4542bacc723b0b51d904ad60ad5f7b097f834ff732bcfed55e9
3
  size 13506236
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37eba3f69a8de2bb10f9da00a9f7fd0d33321a1db800ce0c4f832bed930f498c
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:c9fbbaf41ee09f7cc19b0e4f39d20777ae97e5419a991fd6f23e8e507f1815e4
3
  size 13505370
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda405a586afe2659735839091a537096de8c449498298917ed2a4271bcf1d23
3
  size 13505370
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d43d4124ac450249f0dfc3e09ca5039af0e62120bae80702fab76a8a259517bd
3
- size 275991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d212471ac9ed606f408937249a7e5628c02518c501948c4748bf139807404298
3
+ size 239856
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 443.5, "std_reward": 142.6893478855377, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-11T19:06:51.850782"}
 
1
+ {"mean_reward": 579.5, "std_reward": 324.58011337726776, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-03-11T20:28:44.361438"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d08d5c7bd97111a6988924590b416c90b4cf4a5c980674ca13fd55caa416f077
3
- size 38190
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b992bef57338bbff5f794e37cae66111a52bb5143b5fdc25b5f83eb6aa2aadf
3
+ size 36615