Initial commit
Browse files- README.md +4 -4
- args.yml +2 -2
- config.yml +4 -4
- 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 +1 -1
- dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +1 -1
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
|
@@ -63,7 +63,7 @@ python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f lo
|
|
| 63 |
|
| 64 |
## Hyperparameters
|
| 65 |
```python
|
| 66 |
-
OrderedDict([('batch_size',
|
| 67 |
('buffer_size', 100000),
|
| 68 |
('env_wrapper',
|
| 69 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
|
@@ -71,13 +71,13 @@ OrderedDict([('batch_size', 128),
|
|
| 71 |
('exploration_fraction', 0.1),
|
| 72 |
('frame_stack', 4),
|
| 73 |
('gradient_steps', 1),
|
| 74 |
-
('learning_rate',
|
| 75 |
('learning_starts', 100000),
|
| 76 |
-
('n_timesteps',
|
| 77 |
('optimize_memory_usage', False),
|
| 78 |
('policy', 'CnnPolicy'),
|
| 79 |
('target_update_interval', 1000),
|
| 80 |
-
('train_freq',
|
| 81 |
('normalize', False)])
|
| 82 |
```
|
| 83 |
|
|
|
|
| 63 |
|
| 64 |
## Hyperparameters
|
| 65 |
```python
|
| 66 |
+
OrderedDict([('batch_size', 512),
|
| 67 |
('buffer_size', 100000),
|
| 68 |
('env_wrapper',
|
| 69 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
|
|
|
| 71 |
('exploration_fraction', 0.1),
|
| 72 |
('frame_stack', 4),
|
| 73 |
('gradient_steps', 1),
|
| 74 |
+
('learning_rate', 2.5e-05),
|
| 75 |
('learning_starts', 100000),
|
| 76 |
+
('n_timesteps', 1000000.0),
|
| 77 |
('optimize_memory_usage', False),
|
| 78 |
('policy', 'CnnPolicy'),
|
| 79 |
('target_update_interval', 1000),
|
| 80 |
+
('train_freq', 32),
|
| 81 |
('normalize', False)])
|
| 82 |
```
|
| 83 |
|
args.yml
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
- - eval_episodes
|
| 15 |
- 5
|
| 16 |
- - eval_freq
|
| 17 |
-
-
|
| 18 |
- - gym_packages
|
| 19 |
- []
|
| 20 |
- - hyperparams
|
|
@@ -56,7 +56,7 @@
|
|
| 56 |
- - save_replay_buffer
|
| 57 |
- false
|
| 58 |
- - seed
|
| 59 |
-
-
|
| 60 |
- - storage
|
| 61 |
- null
|
| 62 |
- - study_name
|
|
|
|
| 14 |
- - eval_episodes
|
| 15 |
- 5
|
| 16 |
- - eval_freq
|
| 17 |
+
- 20000
|
| 18 |
- - gym_packages
|
| 19 |
- []
|
| 20 |
- - hyperparams
|
|
|
|
| 56 |
- - save_replay_buffer
|
| 57 |
- false
|
| 58 |
- - seed
|
| 59 |
+
- 3309286548
|
| 60 |
- - storage
|
| 61 |
- null
|
| 62 |
- - study_name
|
config.yml
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - batch_size
|
| 3 |
-
-
|
| 4 |
- - buffer_size
|
| 5 |
- 100000
|
| 6 |
- - env_wrapper
|
|
@@ -14,11 +14,11 @@
|
|
| 14 |
- - gradient_steps
|
| 15 |
- 1
|
| 16 |
- - learning_rate
|
| 17 |
-
-
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
-
-
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- false
|
| 24 |
- - policy
|
|
@@ -26,4 +26,4 @@
|
|
| 26 |
- - target_update_interval
|
| 27 |
- 1000
|
| 28 |
- - train_freq
|
| 29 |
-
-
|
|
|
|
| 1 |
!!python/object/apply:collections.OrderedDict
|
| 2 |
- - - batch_size
|
| 3 |
+
- 512
|
| 4 |
- - buffer_size
|
| 5 |
- 100000
|
| 6 |
- - env_wrapper
|
|
|
|
| 14 |
- - gradient_steps
|
| 15 |
- 1
|
| 16 |
- - learning_rate
|
| 17 |
+
- 2.5e-05
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
+
- 1000000.0
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- false
|
| 24 |
- - policy
|
|
|
|
| 26 |
- - target_update_interval
|
| 27 |
- 1000
|
| 28 |
- - train_freq
|
| 29 |
+
- 32
|
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:f58adf1aa664f858520c84ad6ae193bd2352850fca5803945a01a3eee60ade54
|
| 3 |
+
size 27220123
|
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 sha256:347775f895140e7672be9e1447a679cad5f809e106db2af292aad609901dbaf8
|
| 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:
|
| 3 |
size 13505178
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe25a92409ef331c326674887542aaa6d0bf708bac0428c1b911d61cd5f80149
|
| 3 |
size 13505178
|
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
| 2 |
- Python: 3.10.12
|
| 3 |
- Stable-Baselines3: 2.4.0
|
| 4 |
-
- PyTorch: 2.5.1+
|
| 5 |
- GPU Enabled: False
|
| 6 |
- Numpy: 1.26.4
|
| 7 |
- Cloudpickle: 3.1.0
|
|
|
|
| 1 |
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
|
| 2 |
- Python: 3.10.12
|
| 3 |
- Stable-Baselines3: 2.4.0
|
| 4 |
+
- PyTorch: 2.5.1+cpu
|
| 5 |
- GPU Enabled: False
|
| 6 |
- Numpy: 1.26.4
|
| 7 |
- Cloudpickle: 3.1.0
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward": 268.5, "std_reward": 78.16808811785025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-
|
|
|
|
| 1 |
+
{"mean_reward": 268.5, "std_reward": 78.16808811785025, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-12-03T19:33:29.554666"}
|
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 sha256:009ae66109e75a5090bd285a22494d4dda50b0d95ee85064b48e77bf07632869
|
| 3 |
+
size 5948
|