Initial commit
Browse files- README.md +4 -4
- args.yml +1 -1
- 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
- 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 |
---
|
|
@@ -64,7 +64,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
|
|
| 64 |
## Hyperparameters
|
| 65 |
```python
|
| 66 |
OrderedDict([('batch_size', 64),
|
| 67 |
-
('buffer_size',
|
| 68 |
('env_wrapper',
|
| 69 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
| 70 |
('exploration_final_eps', 0.01),
|
|
@@ -73,10 +73,10 @@ OrderedDict([('batch_size', 64),
|
|
| 73 |
('gradient_steps', 1),
|
| 74 |
('learning_rate', 0.0001),
|
| 75 |
('learning_starts', 50000),
|
| 76 |
-
('n_timesteps',
|
| 77 |
('optimize_memory_usage', False),
|
| 78 |
('policy', 'CnnPolicy'),
|
| 79 |
-
('target_update_interval',
|
| 80 |
('train_freq', 4),
|
| 81 |
('normalize', False)])
|
| 82 |
```
|
|
|
|
| 16 |
type: SpaceInvadersNoFrameskip-v4
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: 487.50 +/- 129.60
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 64 |
## Hyperparameters
|
| 65 |
```python
|
| 66 |
OrderedDict([('batch_size', 64),
|
| 67 |
+
('buffer_size', 100000),
|
| 68 |
('env_wrapper',
|
| 69 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
| 70 |
('exploration_final_eps', 0.01),
|
|
|
|
| 73 |
('gradient_steps', 1),
|
| 74 |
('learning_rate', 0.0001),
|
| 75 |
('learning_starts', 50000),
|
| 76 |
+
('n_timesteps', 1000000.0),
|
| 77 |
('optimize_memory_usage', False),
|
| 78 |
('policy', 'CnnPolicy'),
|
| 79 |
+
('target_update_interval', 10000),
|
| 80 |
('train_freq', 4),
|
| 81 |
('normalize', False)])
|
| 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 |
+
- 1483724856
|
| 60 |
- - storage
|
| 61 |
- null
|
| 62 |
- - study_name
|
config.yml
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
- - - batch_size
|
| 3 |
- 64
|
| 4 |
- - buffer_size
|
| 5 |
-
-
|
| 6 |
- - env_wrapper
|
| 7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
| 8 |
- - exploration_final_eps
|
|
@@ -18,12 +18,12 @@
|
|
| 18 |
- - learning_starts
|
| 19 |
- 50000
|
| 20 |
- - n_timesteps
|
| 21 |
-
-
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- false
|
| 24 |
- - policy
|
| 25 |
- CnnPolicy
|
| 26 |
- - target_update_interval
|
| 27 |
-
-
|
| 28 |
- - train_freq
|
| 29 |
- 4
|
|
|
|
| 2 |
- - - batch_size
|
| 3 |
- 64
|
| 4 |
- - buffer_size
|
| 5 |
+
- 100000
|
| 6 |
- - env_wrapper
|
| 7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
| 8 |
- - exploration_final_eps
|
|
|
|
| 18 |
- - learning_starts
|
| 19 |
- 50000
|
| 20 |
- - n_timesteps
|
| 21 |
+
- 1000000.0
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- false
|
| 24 |
- - policy
|
| 25 |
- CnnPolicy
|
| 26 |
- - target_update_interval
|
| 27 |
+
- 10000
|
| 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 sha256:10537b4299ee9c6f8babc47b0977cca8da8d636a2ff218829d55959122cb41a8
|
| 3 |
+
size 27219622
|
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 13506569
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7946e421a49e442adb9cd55cfb59ec3e1e36dd95279d9e8e804e494984d56ef6
|
| 3 |
size 13506569
|
dqn-SpaceInvadersNoFrameskip-v4/policy.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13505767
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dae4851bdfa38bdd144cf80cb17734b62c391d08dfb98a9878c663513cc24c55
|
| 3 |
size 13505767
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 487.5, "std_reward": 129.6003472217571, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-28T21:37:47.740732"}
|
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 sha256:938cb8cf892f253226d497897e840966f5fb99a29d85bc3bff682e72dd9c75f3
|
| 3 |
+
size 42938
|