GeerBox commited on
Commit
5094ed8
·
verified ·
1 Parent(s): 378146a

Initial commit

Browse files
.ipynb_checkpoints/config-checkpoint.yml ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 512
4
+ - - buffer_size
5
+ - 100000
6
+ - - env_wrapper
7
+ - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
+ - - exploration_final_eps
9
+ - 0.01
10
+ - - exploration_fraction
11
+ - 0.1
12
+ - - frame_stack
13
+ - 4
14
+ - - gradient_steps
15
+ - 1
16
+ - - learning_rate
17
+ - 0.0001
18
+ - - learning_starts
19
+ - 100000
20
+ - - n_timesteps
21
+ - 10000000.0
22
+ - - optimize_memory_usage
23
+ - false
24
+ - - policy
25
+ - CnnPolicy
26
+ - - target_update_interval
27
+ - 1000
28
+ - - train_freq
29
+ - 4
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: 316.00 +/- 132.85
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -64,7 +64,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 512),
67
- ('buffer_size', 100000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 400.50 +/- 173.34
20
  name: mean_reward
21
  verified: false
22
  ---
 
64
  ## Hyperparameters
65
  ```python
66
  OrderedDict([('batch_size', 512),
67
+ ('buffer_size', 50000),
68
  ('env_wrapper',
69
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
  ('exploration_final_eps', 0.01),
args.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
- - dqn.yml
6
  - - device
7
  - auto
8
  - - env
@@ -56,7 +56,7 @@
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
- - 1953177323
60
  - - storage
61
  - null
62
  - - study_name
 
2
  - - - algo
3
  - dqn
4
  - - conf_file
5
+ - dqn_4.yml
6
  - - device
7
  - auto
8
  - - env
 
56
  - - save_replay_buffer
57
  - false
58
  - - seed
59
+ - 2426441547
60
  - - storage
61
  - null
62
  - - study_name
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 512
4
  - - buffer_size
5
- - 100000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
2
  - - - batch_size
3
  - 512
4
  - - buffer_size
5
+ - 50000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57d8ce1bb3567ba0816d81692199bf46250fe9281e25dbd31b108c86fe0e7aee
3
- size 27219646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32755bd92cb76265ce26ef0a7a7f9a326f17f727f7b4fd6af7f950d5ec39336c
3
+ size 27219656
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.7.0a0
 
1
+ 2.8.0
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 sha256:0137c44454468501e7ae064df38ca851be50c44e3a01b45e37a26fdd99f9ddab
3
  size 13506569
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbf83a0309b4a00fc09e54d315e1513bb4cd4580b8ba0e50359ccb0e980e9a81
3
  size 13506569
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e6b9b8dfa582a5523ddc309ef1f6fcd723bc086d6e7e19fd3cb4516d9c53907
3
  size 13505767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09ed1dd1c78adb2d971540416d8d6467fb8619811641d71e7ed09a31a3089dc
3
  size 13505767
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,6 +1,6 @@
1
  - OS: Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39 # 1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
2
  - Python: 3.12.3
3
- - Stable-Baselines3: 2.7.0a0
4
  - PyTorch: 2.7.1+cu126
5
  - GPU Enabled: True
6
  - Numpy: 2.1.3
 
1
  - OS: Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.39 # 1 SMP PREEMPT_DYNAMIC Thu Jun 5 18:30:46 UTC 2025
2
  - Python: 3.12.3
3
+ - Stable-Baselines3: 2.8.0
4
  - PyTorch: 2.7.1+cu126
5
  - GPU Enabled: True
6
  - Numpy: 2.1.3
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 316.0, "std_reward": 132.84953895290718, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-26T14:31:38.879839"}
 
1
+ {"mean_reward": 400.5, "std_reward": 173.34142609312985, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2026-04-13T20:16:56.107206"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fd6d86c33bd9c5df9b6f0b2c3f7f965412bb41ab0e54535861cf2b168518f52
3
- size 395714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1a34e3957d65b772e8ad8037844bfb2b6ffbbf9295fec4afe717e48e1fbf0c6
3
+ size 402661