Initial commit
Browse files- README.md +4 -4
- args.yml +3 -3
- config.yml +3 -3
- 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
- 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 |
---
|
@@ -63,7 +63,7 @@ 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', 0.01),
|
@@ -71,8 +71,8 @@ OrderedDict([('batch_size', 32),
|
|
71 |
('frame_stack', 4),
|
72 |
('gradient_steps', 1),
|
73 |
('learning_rate', 0.0001),
|
74 |
-
('learning_starts',
|
75 |
-
('n_timesteps',
|
76 |
('optimize_memory_usage', False),
|
77 |
('policy', 'CnnPolicy'),
|
78 |
('target_update_interval', 1000),
|
|
|
16 |
type: SpaceInvadersNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 303.00 +/- 116.69
|
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),
|
|
|
71 |
('frame_stack', 4),
|
72 |
('gradient_steps', 1),
|
73 |
('learning_rate', 0.0001),
|
74 |
+
('learning_starts', 10000),
|
75 |
+
('n_timesteps', 500000),
|
76 |
('optimize_memory_usage', False),
|
77 |
('policy', 'CnnPolicy'),
|
78 |
('target_update_interval', 1000),
|
args.yml
CHANGED
@@ -18,9 +18,9 @@
|
|
18 |
- - hyperparams
|
19 |
- null
|
20 |
- - log_folder
|
21 |
-
- logs
|
22 |
- - log_interval
|
23 |
-
-
|
24 |
- - max_total_trials
|
25 |
- null
|
26 |
- - n_eval_envs
|
@@ -54,7 +54,7 @@
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
-
-
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
|
|
18 |
- - hyperparams
|
19 |
- null
|
20 |
- - log_folder
|
21 |
+
- logs
|
22 |
- - log_interval
|
23 |
+
- -1
|
24 |
- - max_total_trials
|
25 |
- null
|
26 |
- - n_eval_envs
|
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 2988924314
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
config.yml
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
- - - batch_size
|
3 |
- 32
|
4 |
- - buffer_size
|
5 |
-
-
|
6 |
- - env_wrapper
|
7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
- - exploration_final_eps
|
@@ -16,9 +16,9 @@
|
|
16 |
- - learning_rate
|
17 |
- 0.0001
|
18 |
- - learning_starts
|
19 |
-
-
|
20 |
- - n_timesteps
|
21 |
-
-
|
22 |
- - optimize_memory_usage
|
23 |
- false
|
24 |
- - policy
|
|
|
2 |
- - - batch_size
|
3 |
- 32
|
4 |
- - buffer_size
|
5 |
+
- 100000
|
6 |
- - env_wrapper
|
7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
- - exploration_final_eps
|
|
|
16 |
- - learning_rate
|
17 |
- 0.0001
|
18 |
- - learning_starts
|
19 |
+
- 10000
|
20 |
- - n_timesteps
|
21 |
+
- 500000
|
22 |
- - optimize_memory_usage
|
23 |
- false
|
24 |
- - policy
|
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:acd4dcf0f363763849ff24272fbf27599c4389de0281adb2157fc9276e78a185
|
3 |
+
size 27224799
|
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 13505739
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00ba158e5da48771388dfc21c4d7644614d2f4095749eb0b22df3b6c90bcc065
|
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:
|
3 |
size 13504937
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11041e6298dcb7a0a44169a82a82eb8df552549bab9e3d7535b07ea73740a0d0
|
3 |
size 13504937
|
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
- Python: 3.8.16
|
3 |
- Stable-Baselines3: 1.7.0
|
4 |
-
- PyTorch: 1.13.
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.21.6
|
7 |
- Gym: 0.21.0
|
|
|
1 |
- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
- Python: 3.8.16
|
3 |
- Stable-Baselines3: 1.7.0
|
4 |
+
- PyTorch: 1.13.1+cu116
|
5 |
- GPU Enabled: True
|
6 |
- Numpy: 1.21.6
|
7 |
- Gym: 0.21.0
|
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:b09cc7553b32ead61e40e66b8ab1524695053eb100bcc97d95942acaed9db542
|
3 |
+
size 233359
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 303.0, "std_reward": 116.68761716651858, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-01-12T08:49:15.043707"}
|
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 sha256:3f3570630f549696b128148eea25cdf8d09ad25e56dc421f8f9a9ae365997812
|
3 |
+
size 21283
|