Hugging Face's logo

1itai1
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
1itai1 commited on
Commit
116b5e9
·
1 Parent(s): 14c6393

Initial commit

Browse files
Files changed (12) hide show
  1. README.md +2 -2
  2. args.yml +1 -1
  3. config.yml +1 -1
  4. dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
  5. dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -1
  6. dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  9. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  10. replay.mp4 +2 -2
  11. results.json +1 -1
  12. 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: 349.00 +/- 207.90
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', 2056),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
 
16
  type: SpaceInvadersNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: 617.50 +/- 111.23
20
  name: mean_reward
21
  verified: false
22
  ---
 
62
 
63
  ## Hyperparameters
64
  ```python
65
+ OrderedDict([('batch_size', 32),
66
  ('buffer_size', 100000),
67
  ('env_wrapper',
68
  ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 1875358187
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3865630491
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 2056
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
 
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
+ - 32
4
  - - buffer_size
5
  - 100000
6
  - - env_wrapper
dqn-SpaceInvadersNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ada2e215d7009b1270408110c731872366dd7fda41af62a9d15985fa9411d0a5
3
- size 27224823
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9806d70b5694d950efcbcb778760e55ac86c744106089b9057112309e735272a
3
+ size 27224819
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 1.8.0a10
 
1
+ 1.8.0a13
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 sha256:65376fcfc05a73eda03d73d0591218a4ee5a2f31bdd227fbb12d9a49e8203560
3
  size 13505739
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c631913030052bafa1d8b9db185a1a6cfa6b1ebee98b87c04d1aaaab0f12ef51
3
  size 13505739
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17422b78d16abf3a189aa58c14a04ffb30ffb8d9c20f72a55d5d318c5a4a39dd
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6305c0b4f4cede0a9e6e4db91dbe48cedecaa481ddf15d6414a7ca5e59dbe94c
3
  size 13504937
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -1,6 +1,6 @@
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: 1.8.0a10
4
  - PyTorch: 1.13.1+cu116
5
  - GPU Enabled: True
6
  - Numpy: 1.22.4
 
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: 1.8.0a13
4
  - PyTorch: 1.13.1+cu116
5
  - GPU Enabled: True
6
  - Numpy: 1.22.4
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9da41a61448a285525744e46d00c96b1d6acaaf04acd8eb33d47b1abb438de9b
3
- size 247414
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1837de64042b6a1630dfa725ac4ef14b9344c87b2b085a515a5647f6587b71b6
3
+ size 199959
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 349.0, "std_reward": 207.90382391865717, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-29T18:16:35.226151"}
 
1
+ {"mean_reward": 617.5, "std_reward": 111.22612103278618, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-01T20:15:59.200439"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c17a6c32150e2bd2e5339442ba75cc5d1c1aee2f2fc1bee279ebdbdd5068dd5
3
- size 15037
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6c6aaa9eb5e36ba9299309ee70ecf888ca3de0577d13292b560f8e79af38a20
3
+ size 36927