Initial commit
Browse files- README.md +11 -11
- args.yml +1 -1
- config.yml +10 -10
- dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
- dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
- replay.mp4 +2 -2
- results.json +1 -1
- 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:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
@@ -63,20 +63,20 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
|
|
63 |
## Hyperparameters
|
64 |
```python
|
65 |
OrderedDict([('batch_size', 32),
|
66 |
-
('buffer_size',
|
67 |
('env_wrapper',
|
68 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
69 |
-
('exploration_final_eps', 0.
|
70 |
-
('exploration_fraction', 0.
|
71 |
-
('frame_stack',
|
72 |
-
('gradient_steps',
|
73 |
-
('learning_rate', 0.
|
74 |
-
('learning_starts',
|
75 |
-
('n_timesteps',
|
76 |
('optimize_memory_usage', False),
|
77 |
('policy', 'CnnPolicy'),
|
78 |
-
('target_update_interval',
|
79 |
-
('train_freq',
|
80 |
('normalize', False)])
|
81 |
```
|
82 |
|
|
|
16 |
type: SpaceInvadersNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 628.00 +/- 248.45
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
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', 4),
|
72 |
+
('gradient_steps', 1),
|
73 |
+
('learning_rate', 0.0001),
|
74 |
+
('learning_starts', 100000),
|
75 |
+
('n_timesteps', 600000.0),
|
76 |
('optimize_memory_usage', False),
|
77 |
('policy', 'CnnPolicy'),
|
78 |
+
('target_update_interval', 1000),
|
79 |
+
('train_freq', 4),
|
80 |
('normalize', False)])
|
81 |
```
|
82 |
|
args.yml
CHANGED
@@ -56,7 +56,7 @@
|
|
56 |
- - save_replay_buffer
|
57 |
- false
|
58 |
- - seed
|
59 |
-
-
|
60 |
- - storage
|
61 |
- null
|
62 |
- - study_name
|
|
|
56 |
- - save_replay_buffer
|
57 |
- false
|
58 |
- - seed
|
59 |
+
- 3015735485
|
60 |
- - storage
|
61 |
- null
|
62 |
- - study_name
|
config.yml
CHANGED
@@ -2,28 +2,28 @@
|
|
2 |
- - - batch_size
|
3 |
- 32
|
4 |
- - buffer_size
|
5 |
-
-
|
6 |
- - env_wrapper
|
7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
- - exploration_final_eps
|
9 |
-
- 0.
|
10 |
- - exploration_fraction
|
11 |
-
- 0.
|
12 |
- - frame_stack
|
13 |
-
-
|
14 |
- - gradient_steps
|
15 |
-
-
|
16 |
- - learning_rate
|
17 |
-
- 0.
|
18 |
- - learning_starts
|
19 |
-
-
|
20 |
- - n_timesteps
|
21 |
-
-
|
22 |
- - optimize_memory_usage
|
23 |
- false
|
24 |
- - policy
|
25 |
- CnnPolicy
|
26 |
- - target_update_interval
|
27 |
-
-
|
28 |
- - train_freq
|
29 |
-
-
|
|
|
2 |
- - - batch_size
|
3 |
- 32
|
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 |
+
- 600000.0
|
22 |
- - optimize_memory_usage
|
23 |
- false
|
24 |
- - policy
|
25 |
- CnnPolicy
|
26 |
- - target_update_interval
|
27 |
+
- 1000
|
28 |
- - train_freq
|
29 |
+
- 4
|
dqn-SpaceInvadersNoFrameskip-v4.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b251b41dcb65eab7515469bb3eaef1c11a627e44017eed65a85b5992c4efcfe7
|
3 |
+
size 27220653
|
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51431cce95e2070bdacb46136bb9341809afbaa373ec7eeac34b86cc0e06231e
|
3 |
+
size 13506172
|
dqn-SpaceInvadersNoFrameskip-v4/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:215816c0edc5c9557c91391777e1ca527ab1536848c08dc58d558e01518d34e5
|
3 |
+
size 13505370
|
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.4.0a7
|
4 |
- PyTorch: 2.3.1+cu121
|
5 |
-
- GPU Enabled:
|
6 |
- Numpy: 1.23.5
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.29.1
|
|
|
2 |
- Python: 3.10.12
|
3 |
- Stable-Baselines3: 2.4.0a7
|
4 |
- PyTorch: 2.3.1+cu121
|
5 |
+
- GPU Enabled: True
|
6 |
- Numpy: 1.23.5
|
7 |
- Cloudpickle: 2.2.1
|
8 |
- Gymnasium: 0.29.1
|
replay.mp4
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a04bca4e8c24bd6153d5397ee2df8c7e1b8c9efadabe3ac3787f6c7ae536efd0
|
3 |
+
size 259831
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 628.0, "std_reward": 248.44717748447053, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-23T16:16:34.158604"}
|
train_eval_metrics.zip
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4a4a5195a332a2f20d751fdb7ab0cb9c22bbf9a075eb34e8233aed3dea0494b
|
3 |
+
size 24836
|