Upload folder using huggingface_hub
Browse files- .gitattributes +0 -1
- README.md +5 -11
- args.yml +4 -6
- config.yml +1 -1
- dqn-SpaceInvadersNoFrameskip-v4.zip +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -1
- dqn-SpaceInvadersNoFrameskip-v4/data +0 -0
- dqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/policy.pth +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +6 -8
- env_kwargs.yml +1 -1
- replay.mp4 +3 -0
- results.json +1 -1
- train_eval_metrics.zip +2 -2
.gitattributes
CHANGED
|
@@ -25,7 +25,6 @@
|
|
| 25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 28 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 29 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
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 |
---
|
|
@@ -35,7 +35,6 @@ with hyperparameter optimization and pre-trained agents included.
|
|
| 35 |
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
| 36 |
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
| 37 |
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
| 38 |
-
SBX (SB3 + Jax): https://github.com/araffin/sbx
|
| 39 |
|
| 40 |
Install the RL Zoo (with SB3 and SB3-Contrib):
|
| 41 |
```bash
|
|
@@ -44,13 +43,13 @@ pip install rl_zoo3
|
|
| 44 |
|
| 45 |
```
|
| 46 |
# Download model and save it into the logs/ folder
|
| 47 |
-
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga
|
| 48 |
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
| 49 |
```
|
| 50 |
|
| 51 |
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
| 52 |
```
|
| 53 |
-
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga
|
| 54 |
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
| 55 |
```
|
| 56 |
|
|
@@ -58,7 +57,7 @@ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
|
| 58 |
```
|
| 59 |
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
| 60 |
# Upload the model and generate video (when possible)
|
| 61 |
-
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga
|
| 62 |
```
|
| 63 |
|
| 64 |
## Hyperparameters
|
|
@@ -73,15 +72,10 @@ OrderedDict([('batch_size', 32),
|
|
| 73 |
('gradient_steps', 1),
|
| 74 |
('learning_rate', 0.0001),
|
| 75 |
('learning_starts', 100000),
|
| 76 |
-
('n_timesteps',
|
| 77 |
('optimize_memory_usage', False),
|
| 78 |
('policy', 'CnnPolicy'),
|
| 79 |
('target_update_interval', 1000),
|
| 80 |
('train_freq', 4),
|
| 81 |
('normalize', False)])
|
| 82 |
```
|
| 83 |
-
|
| 84 |
-
# Environment Arguments
|
| 85 |
-
```python
|
| 86 |
-
{'render_mode': 'rgb_array'}
|
| 87 |
-
```
|
|
|
|
| 16 |
type: SpaceInvadersNoFrameskip-v4
|
| 17 |
metrics:
|
| 18 |
- type: mean_reward
|
| 19 |
+
value: 889.50 +/- 289.46
|
| 20 |
name: mean_reward
|
| 21 |
verified: false
|
| 22 |
---
|
|
|
|
| 35 |
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
| 36 |
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
| 37 |
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
|
|
|
| 38 |
|
| 39 |
Install the RL Zoo (with SB3 and SB3-Contrib):
|
| 40 |
```bash
|
|
|
|
| 43 |
|
| 44 |
```
|
| 45 |
# Download model and save it into the logs/ folder
|
| 46 |
+
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga HaiderAUT -f logs/
|
| 47 |
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
| 48 |
```
|
| 49 |
|
| 50 |
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
| 51 |
```
|
| 52 |
+
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga HaiderAUT -f logs/
|
| 53 |
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
| 54 |
```
|
| 55 |
|
|
|
|
| 57 |
```
|
| 58 |
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
| 59 |
# Upload the model and generate video (when possible)
|
| 60 |
+
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga HaiderAUT
|
| 61 |
```
|
| 62 |
|
| 63 |
## Hyperparameters
|
|
|
|
| 72 |
('gradient_steps', 1),
|
| 73 |
('learning_rate', 0.0001),
|
| 74 |
('learning_starts', 100000),
|
| 75 |
+
('n_timesteps', 10000000.0),
|
| 76 |
('optimize_memory_usage', False),
|
| 77 |
('policy', 'CnnPolicy'),
|
| 78 |
('target_update_interval', 1000),
|
| 79 |
('train_freq', 4),
|
| 80 |
('normalize', False)])
|
| 81 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
args.yml
CHANGED
|
@@ -2,15 +2,13 @@
|
|
| 2 |
- - - algo
|
| 3 |
- dqn
|
| 4 |
- - conf_file
|
| 5 |
-
-
|
| 6 |
- - device
|
| 7 |
- auto
|
| 8 |
- - env
|
| 9 |
- SpaceInvadersNoFrameskip-v4
|
| 10 |
- - env_kwargs
|
| 11 |
- null
|
| 12 |
-
- - eval_env_kwargs
|
| 13 |
-
- null
|
| 14 |
- - eval_episodes
|
| 15 |
- 5
|
| 16 |
- - eval_freq
|
|
@@ -56,7 +54,7 @@
|
|
| 56 |
- - save_replay_buffer
|
| 57 |
- false
|
| 58 |
- - seed
|
| 59 |
-
-
|
| 60 |
- - storage
|
| 61 |
- null
|
| 62 |
- - study_name
|
|
@@ -67,8 +65,6 @@
|
|
| 67 |
- false
|
| 68 |
- - trained_agent
|
| 69 |
- ''
|
| 70 |
-
- - trial_id
|
| 71 |
-
- null
|
| 72 |
- - truncate_last_trajectory
|
| 73 |
- true
|
| 74 |
- - uuid
|
|
@@ -83,3 +79,5 @@
|
|
| 83 |
- sb3
|
| 84 |
- - wandb_tags
|
| 85 |
- []
|
|
|
|
|
|
|
|
|
| 2 |
- - - algo
|
| 3 |
- dqn
|
| 4 |
- - conf_file
|
| 5 |
+
- null
|
| 6 |
- - device
|
| 7 |
- auto
|
| 8 |
- - env
|
| 9 |
- SpaceInvadersNoFrameskip-v4
|
| 10 |
- - env_kwargs
|
| 11 |
- null
|
|
|
|
|
|
|
| 12 |
- - eval_episodes
|
| 13 |
- 5
|
| 14 |
- - eval_freq
|
|
|
|
| 54 |
- - save_replay_buffer
|
| 55 |
- false
|
| 56 |
- - seed
|
| 57 |
+
- 2243915477
|
| 58 |
- - storage
|
| 59 |
- null
|
| 60 |
- - study_name
|
|
|
|
| 65 |
- false
|
| 66 |
- - trained_agent
|
| 67 |
- ''
|
|
|
|
|
|
|
| 68 |
- - truncate_last_trajectory
|
| 69 |
- true
|
| 70 |
- - uuid
|
|
|
|
| 79 |
- sb3
|
| 80 |
- - wandb_tags
|
| 81 |
- []
|
| 82 |
+
- - yaml_file
|
| 83 |
+
- null
|
config.yml
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
-
-
|
| 22 |
- - optimize_memory_usage
|
| 23 |
- false
|
| 24 |
- - policy
|
|
|
|
| 18 |
- - learning_starts
|
| 19 |
- 100000
|
| 20 |
- - n_timesteps
|
| 21 |
+
- 10000000.0
|
| 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:c706d585845776535bada5f6b6c6753dfb610b1bc3d15bb1c13e967b1f00bd0c
|
| 3 |
+
size 27225013
|
dqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
1.8.0a2
|
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 sha256:6e47ab09ab431c14712f926a60c2bc21578b6e870c7ac2074cd22997ff9e2fd6
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bd94d828fe365b570bcccf70f03facd27714afdc63d90a3ebe8de184491ebb2
|
| 3 |
+
size 13504937
|
dqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.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:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
| 3 |
+
size 431
|
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt
CHANGED
|
@@ -1,9 +1,7 @@
|
|
| 1 |
-
- OS: Linux-
|
| 2 |
-
- Python: 3.
|
| 3 |
-
- Stable-Baselines3:
|
| 4 |
-
- PyTorch:
|
| 5 |
- GPU Enabled: True
|
| 6 |
-
- Numpy:
|
| 7 |
-
-
|
| 8 |
-
- Gymnasium: 1.2.1
|
| 9 |
-
- OpenAI Gym: 0.25.2
|
|
|
|
| 1 |
+
- OS: Linux-5.10.16.3-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Apr 2 22:23:49 UTC 2021
|
| 2 |
+
- Python: 3.10.9
|
| 3 |
+
- Stable-Baselines3: 1.8.0a2
|
| 4 |
+
- PyTorch: 1.13.1+cu117
|
| 5 |
- GPU Enabled: True
|
| 6 |
+
- Numpy: 1.23.5
|
| 7 |
+
- Gym: 0.21.0
|
|
|
|
|
|
env_kwargs.yml
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
{}
|
replay.mp4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ccb65236a5ee88da2137e25b6cc987c96a8e733ede307a5b0a966ec0506b2d
|
| 3 |
+
size 171038
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"mean_reward":
|
|
|
|
| 1 |
+
{"mean_reward": 889.5, "std_reward": 289.4602736128051, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-03-01T11:15:20.817406"}
|
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 sha256:420fa535f2be84f821d3163b122aada33786f8068ec431d781c2d446f06568b5
|
| 3 |
+
size 270929
|