Hugging Face's logo

zlicastro
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files
xet
Community
zlicastro commited on
Commit
1104e8b
·
1 Parent(s): e7981af

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +2 -2
  2. args.yml +2 -2
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +5 -5
  9. replay.mp4 +2 -2
  10. results.json +1 -1
  11. 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: 582.00 +/- 181.28
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -58,7 +58,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 64),
61
- ('buffer_size', 200000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 534.50 +/- 40.52
20
  name: mean_reward
21
  verified: false
22
  ---
 
58
  ## Hyperparameters
59
  ```python
60
  OrderedDict([('batch_size', 64),
61
+ ('buffer_size', 125000),
62
  ('env_wrapper',
63
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
64
  ('exploration_final_eps', 0.01),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 453092863
58
  - - storage
59
  - null
60
  - - study_name
@@ -64,7 +64,7 @@
64
  - - track
65
  - false
66
  - - trained_agent
67
- - /content/rl-baselines3-zoo/logs/dqn/SpaceInvadersNoFrameskip-v4_3/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1310472720
58
  - - storage
59
  - null
60
  - - study_name
 
64
  - - track
65
  - false
66
  - - trained_agent
67
+ - C:/Users/Zack_/Desktop/ZacksFiles/Obsidian/ZacksVault/AIDev/HuggingFaceRLCourse/Notebooks/rl-baselines3-zoo/logs/dqn/SpaceInvadersNoFrameskip-v4_7/SpaceInvadersNoFrameskip-v4.zip
68
  - - truncate_last_trajectory
69
  - true
70
  - - uuid
config.yml CHANGED
@@ -2,7 +2,7 @@
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
- - 200000
6
  - - env_wrapper
7
  - - stable_baselines3.common.atari_wrappers.AtariWrapper
8
  - - exploration_final_eps
 
2
  - - - batch_size
3
  - 64
4
  - - buffer_size
5
+ - 125000
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:e79fae8da414e5666072d13ee41f0b72005fcc39d4c05f24835c67c81757689e
3
- size 27224795
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d1af58181949a8f069e21465ca6add9dddfd5643874c2ab277308631c78a1b3
3
+ size 27224043
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 sha256:9c3e1c0a03458ac5fc2f8b3fbd5ffe8c345c67cd4adece770d28b649fe119fd6
3
- size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6181c1ae857371c1d61198fcc6b89c8c062367c354e30743e32dcbca66ff437
3
+ size 13505419
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc3e51a5af85fb736b363c1a11c8f27dddd4506dd45e4fb3255783b62b385a3c
3
- size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3506bd7eda575f2f5a3e2827cfea64cf29d0e1bec9a4f6baec0eed7bc05ad0b
3
+ size 13504745
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,7 +1,7 @@
1
- OS: Linux-5.10.133+-x86_64-with-glibc2.27 #1 SMP Fri Aug 26 08:44:51 UTC 2022
2
- Python: 3.8.16
3
  Stable-Baselines3: 1.7.0a10
4
- PyTorch: 1.13.0+cu116
5
- GPU Enabled: True
6
- Numpy: 1.21.6
7
  Gym: 0.21.0
 
1
+ OS: Windows-10-10.0.19041-SP0 10.0.19041
2
+ Python: 3.8.5
3
  Stable-Baselines3: 1.7.0a10
4
+ PyTorch: 1.13.1+cpu
5
+ GPU Enabled: False
6
+ Numpy: 1.23.5
7
  Gym: 0.21.0
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fe0f60bb212db8a93e6cce664dc2cf8796a3d8fee4b9dbd39b0505acdd98a19
3
- size 211671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede4d1a7623ee7161a33a33c06288a53baa561765a8dce28ad058b4f87b8da8b
3
+ size 188680
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 582.0, "std_reward": 181.27603261324978, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T02:56:13.720602"}
 
1
+ {"mean_reward": 534.5, "std_reward": 40.52468383590426, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-02T15:25:38.819298"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a15662ca2371a926ab3942f6694bcf3ed2f94aa73f5abb05302dfee72627ef3
3
- size 53922
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9f8b5e051d3c18f15544b02c8bfb9ce2f678ac0641ab21f997cca0679eee29
3
+ size 57105