YarramsettiNaresh commited on
Commit
9007c89
1 Parent(s): b834fab

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 128.00 +/- 49.86
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,17 +62,17 @@ 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']),
69
  ('exploration_final_eps', 0.01),
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),
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: 139.00 +/- 61.02
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 128),
66
+ ('buffer_size', 1000000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 4),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 1e-06),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 10000000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
- - logs2/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1611369050
58
  - - storage
59
  - null
60
  - - study_name
 
18
  - - hyperparams
19
  - null
20
  - - log_folder
21
+ - logs5/
22
  - - log_interval
23
  - -1
24
  - - max_total_trials
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1497195639
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,8 +1,8 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 32
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
@@ -14,11 +14,11 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 0.0001
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 1000000
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 128
4
  - - buffer_size
5
+ - 1000000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 1.0e-06
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 10000000.0
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:c5192ed63a434797535d48ac9ccb25f9a7c15feeff655ca96813d00b987c6d96
3
- size 13709288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b7308934101deabc280e51f46d2a5ac5cd897c4d0cd171ed85b030d4f01701
3
+ size 13709215
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 sha256:0b69a6cb94f8a9599ea4291f66c0618fbf541f7509cd0bdc82e64322acea359b
3
  size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81abf2e1628e006879e47273d60bdc52aeebf32546d72a76ed96ef912f50d023
3
  size 687
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0164dfb8103edfdcac15663573bfc80dc6585dcfc93ee4533252692be342175b
3
  size 13504745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c18975707e17ad8562413b0601e0f31d192603aab1b37ecaf4e2c13eff2fcf1
3
  size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,4 +1,4 @@
1
- - OS: Linux-5.15.0-1038-oracle-x86_64-with-glibc2.35 # 44-Ubuntu SMP Thu Jun 22 03:34:25 UTC 2023
2
  - Python: 3.10.6
3
  - Stable-Baselines3: 2.0.0
4
  - PyTorch: 2.0.1+cu117
 
1
+ - OS: Linux-5.15.0-1039-oracle-x86_64-with-glibc2.35 # 45-Ubuntu SMP Thu Jul 13 19:37:23 UTC 2023
2
  - Python: 3.10.6
3
  - Stable-Baselines3: 2.0.0
4
  - PyTorch: 2.0.1+cu117
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a6976c90010e664a9463bc6bf7c177531305c6d63183da5236936acab10a589
3
- size 249457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564c30ad614968e19b7da9d960f1767db1376e1c49e5c26df1fb357cfbed11da
3
+ size 243037
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 128.0, "std_reward": 49.85980344927164, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-26T03:46:45.653388"}
 
1
+ {"mean_reward": 139.0, "std_reward": 61.02458520956943, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-26T14:52:23.477170"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08f3f851d87058a026099e91007739f25163791f9d8b4c7b99e49bf7fe3ef36b
3
- size 268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda0e827fe9cdb5f59f1b71942d3af395c18612049de42510faccc7acb89059b
3
+ size 225