Hugging Face's logo

juan9
/
dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning
stable-baselines3
SpaceInvadersNoFrameskip-v4
deep-reinforcement-learning
Eval Results
Model card Files Community
juan9 commited on
Commit
32c8916
•
1 Parent(s): 6c5b171

Initial commit

Browse files
Files changed (11) 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/data +0 -0
  6. dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
  7. dqn-SpaceInvadersNoFrameskip-v4/policy.pth +1 -1
  8. dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
  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: 235.50 +/- 111.66
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', 64),
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: 350.00 +/- 165.06
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
- - 590744676
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 1491742706
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -1,6 +1,6 @@
1
  !!python/object/apply:collections.OrderedDict
2
  - - - batch_size
3
- - 64
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:b591521438f505c16a3f32342319640288ce607845234499920de4a6f69c2af3
3
- size 27219560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e209f58bdf5ec0378b135de8d3ef8436c2615ceb54573a79e18b652f027005ba
3
+ size 27219634
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:cfef53b55c4349c35ac313cc6fbdb04d7e11c06051ef8bfc55c3451be14cec16
3
  size 13505852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae180944bcee62bc06cce19d7d737d3fd601082756704f3045ad644679199e69
3
  size 13505852
dqn-SpaceInvadersNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21307c31e748d832d6bc9ec22ae1befd9e328cabbeb8a0406d229eb31672eb58
3
  size 13505178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201d49bff4a35b90fc3a93448e5624f9c2873d0a9e53a759013df6590a15c451
3
  size 13505178
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt CHANGED
@@ -3,7 +3,7 @@
3
  - Stable-Baselines3: 2.3.0a2
4
  - PyTorch: 2.1.0+cu121
5
  - GPU Enabled: False
6
- - Numpy: 1.23.5
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
 
3
  - Stable-Baselines3: 2.3.0a2
4
  - PyTorch: 2.1.0+cu121
5
  - GPU Enabled: False
6
+ - Numpy: 1.25.2
7
  - Cloudpickle: 2.2.1
8
  - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.26.2
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f20ff464de9dbb7bf47341ab80021a7e00d2550a48bd3538c2af6ded04caab36
3
- size 263552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa874d16b63bcd7012873ff68685494f13f9506c62079f459bff9a29a19b1387
3
+ size 253120
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": 235.5, "std_reward": 111.65684036367857, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-13T17:07:23.133070"}
 
1
+ {"mean_reward": 350.0, "std_reward": 165.0605949341029, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-02-13T21:53:21.847857"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c68485e2ea2c8a559e270578db3b334fa03e3043fc73927ba49c087848faf5e
3
- size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b227827451587431fcccc5fe9f377e7bf8fbbfe0f0a09a1f487228d409441f1
3
+ size 13409