ljones commited on
Commit
c1f20de
·
1 Parent(s): 95d63e1

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: 331.50 +/- 202.66
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -62,15 +62,15 @@ 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', 6),
72
  ('gradient_steps', 1),
73
- ('learning_rate', 5e-05),
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: 768.50 +/- 225.58
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 24),
66
+ ('buffer_size', 75000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
69
  ('exploration_final_eps', 0.01),
70
  ('exploration_fraction', 0.1),
71
  ('frame_stack', 6),
72
  ('gradient_steps', 1),
73
+ ('learning_rate', 0.0002),
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
- - 401089548
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3726811782
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
@@ -14,7 +14,7 @@
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
- - 5.0e-05
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 24
4
  - - buffer_size
5
+ - 75000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
14
  - - gradient_steps
15
  - 1
16
  - - learning_rate
17
+ - 0.0002
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 sha256:8506ba7ea3d50a5427000d2ed9db2d3fe72c8682659ad48d92725662945d842b
3
- size 27386243
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda7be6f57e5cf4883654f8c2b0fb9e1a8cebb72e7cca0e3487385939fdf68fd
3
+ size 27386253
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:e9fb5a31f1d3da6ee01039e3e9f4f8db1ce2c2a3946d5b8a5afd1846e83b4188
3
  size 13538507
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:116b124c1466a2c4c5904cc2ee20776f112ce1728409502ed351e1bc29be6559
3
  size 13538507
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e19f16c0666d7d336979766a9be792ffca2f19e8433a234501ce4668bb0c9c57
3
  size 13537705
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f76a6336df8ba9a2e0e299136058c57f6ff08614a1d18f25d64ce4740c72fc
3
  size 13537705
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,5 +1,5 @@
1
- - OS: Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
- - Python: 3.8.10
3
  - Stable-Baselines3: 1.8.0a2
4
  - PyTorch: 1.13.1+cu116
5
  - GPU Enabled: True
 
1
+ - OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
2
+ - Python: 3.9.16
3
  - Stable-Baselines3: 1.8.0a2
4
  - PyTorch: 1.13.1+cu116
5
  - GPU Enabled: True
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1638aa33dc137b6bd55f9ee589dd7d50a2e619dad082791d7cb1810927c8ef8c
3
- size 260433
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839d8e05a8425cc53ed55a3b7f8d9f72de8abc02f880c9b6044b5bb641db8290
3
+ size 189342
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 331.5, "std_reward": 202.6579630806547, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-08T13:23:23.649151"}
 
1
+ {"mean_reward": 768.5, "std_reward": 225.57759197225243, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-09T18:32:36.192958"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6b5ad262e7a5eb41961e22602e5f808fce9c3dc417a22876c264089e4a25466
3
- size 40019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043273d388c002ff603f0f9bfa6138de9d4606f253955e7589b0fb474966b963
3
+ size 35866