Initial commit
Browse files- README.md +11 -12
- args.yml +1 -1
- config.yml +9 -9
- dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
- dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +1 -1
- dqn-SpaceInvadersNoFrameskip-v4/policy.pth +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 |
---
|
@@ -62,23 +62,22 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
|
|
62 |
|
63 |
## Hyperparameters
|
64 |
```python
|
65 |
-
OrderedDict([('batch_size',
|
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', 4),
|
72 |
-
('gamma', 0.
|
73 |
('gradient_steps', 1),
|
74 |
-
('learning_rate',
|
75 |
-
('learning_starts',
|
76 |
('n_timesteps', 100000.0),
|
77 |
-
('
|
78 |
('policy', 'CnnPolicy'),
|
79 |
-
('target_update_interval',
|
80 |
-
('train_freq', 4)
|
81 |
-
('normalize', False)])
|
82 |
```
|
83 |
|
84 |
# Environment Arguments
|
|
|
16 |
type: SpaceInvadersNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 390.50 +/- 145.92
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
|
|
62 |
|
63 |
## Hyperparameters
|
64 |
```python
|
65 |
+
OrderedDict([('batch_size', 64),
|
66 |
+
('buffer_size', 1000000),
|
67 |
('env_wrapper',
|
68 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
69 |
+
('exploration_final_eps', 0.01),
|
70 |
+
('exploration_fraction', 0.025),
|
71 |
('frame_stack', 4),
|
72 |
+
('gamma', 0.99),
|
73 |
('gradient_steps', 1),
|
74 |
+
('learning_rate', 5e-05),
|
75 |
+
('learning_starts', 50000),
|
76 |
('n_timesteps', 100000.0),
|
77 |
+
('normalize', False),
|
78 |
('policy', 'CnnPolicy'),
|
79 |
+
('target_update_interval', 10000),
|
80 |
+
('train_freq', 4)])
|
|
|
81 |
```
|
82 |
|
83 |
# Environment Arguments
|
args.yml
CHANGED
@@ -54,7 +54,7 @@
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
-
-
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 2957842650
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
config.yml
CHANGED
@@ -1,31 +1,31 @@
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - batch_size
|
3 |
-
-
|
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 |
- 4
|
14 |
- - gamma
|
15 |
-
- 0.
|
16 |
- - gradient_steps
|
17 |
- 1
|
18 |
- - learning_rate
|
19 |
-
-
|
20 |
- - learning_starts
|
21 |
-
-
|
22 |
- - n_timesteps
|
23 |
- 100000.0
|
24 |
-
- -
|
25 |
- false
|
26 |
- - policy
|
27 |
- CnnPolicy
|
28 |
- - target_update_interval
|
29 |
-
-
|
30 |
- - train_freq
|
31 |
- 4
|
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - batch_size
|
3 |
+
- 64
|
4 |
- - buffer_size
|
5 |
+
- 1000000
|
6 |
- - env_wrapper
|
7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
- - exploration_final_eps
|
9 |
+
- 0.01
|
10 |
- - exploration_fraction
|
11 |
+
- 0.025
|
12 |
- - frame_stack
|
13 |
- 4
|
14 |
- - gamma
|
15 |
+
- 0.99
|
16 |
- - gradient_steps
|
17 |
- 1
|
18 |
- - learning_rate
|
19 |
+
- 5.0e-05
|
20 |
- - learning_starts
|
21 |
+
- 50000
|
22 |
- - n_timesteps
|
23 |
- 100000.0
|
24 |
+
- - normalize
|
25 |
- false
|
26 |
- - policy
|
27 |
- CnnPolicy
|
28 |
- - target_update_interval
|
29 |
+
- 10000
|
30 |
- - train_freq
|
31 |
- 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 sha256:38d005501e227a0f29d2655e0fbc99ed1bb0667086241662842a33f51074c39c
|
3 |
+
size 27220129
|
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 13506236
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0db2e3b8c2168aa9ea8430b472d56db222b82461c9a8182eead1c057309a19bb
|
3 |
size 13506236
|
dqn-SpaceInvadersNoFrameskip-v4/policy.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13505370
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14cb70e22cd28ab4c9c6d60aa9439f46666e95a3479c04910dd3d3933a753560
|
3 |
size 13505370
|
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 sha256:668f5267ab783777567b8c7f33c27b372a8b413e0a52bd31f23ecc08b00dba5e
|
3 |
+
size 257293
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 390.5, "std_reward": 145.91864171516949, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-01-01T16:41:16.100047"}
|
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 sha256:22f2ae568f607e7d6d4aea704e318b1f5c7221fc4b47bec5c9e0e5208fe4249f
|
3 |
+
size 5374
|