Hugging Face's logo

jakubgajski
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
jakubgajski commited on
Commit
36b9f30
·
1 Parent(s): 79bcd3c

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: 494.50 +/- 147.37
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', 64),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 64),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0002),
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: 412.00 +/- 165.95
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']),
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0002),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 3000000.0),
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
- - 229533310
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3043986619
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
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
+ - 128
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 3000000.0
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 sha256:7e11bfb95a8058d234779815a9da41bda6d873eda196d37affbd3b89d9e71041
3
- size 27224860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d636f5d1e4c53139e19011bda994556c5ea5df999675030126e09eae79878ce
3
+ size 27224862
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 sha256:528fd5c56702a046551e48eed51a44b27a2ba154232b13fb52f0c37efc7767a2
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfbc5df1ef88eb073d126d29a8359ad58985f0d8216820eb29302a666288da6
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d4cee9f93d161d17b1f38647c486b85513bd39a8358f37895ef924f43dfad89
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31359373678f187fa4bd5a5d1295caf614200d0ab885f2d07ea4f594bce0bb45
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4856b13a576661c2fa1395e8bc78e152231e7107d98c5c6af5aba46e13582dc
3
- size 250163
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2412ee5e9d9c5dc5bf32832d1794d06fcbfe947cb2916148616ddac118778357
3
+ size 196503
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 494.5, "std_reward": 147.3677373104439, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-28T12:17:47.214277"}
 
1
+ {"mean_reward": 412.0, "std_reward": 165.9548131269473, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-04T14:39:43.831134"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:697e351a5cdd2f36aef7c8c113a2841c163a3b1fa10c876c5914ed40daf6014a
3
- size 34525
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010d31b068fdf909a2db03c2519338380cbd1489047c9d095af79f50377df308
3
+ size 107967