Initial commit
Browse files- README.md +12 -20
- args.yml +2 -2
- config.yml +2 -18
- qrdqn-SpaceInvadersNoFrameskip-v4.zip +3 -0
- qrdqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version +1 -0
- qrdqn-SpaceInvadersNoFrameskip-v4/data +0 -0
- qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth +3 -0
- qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth +3 -0
- qrdqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth +3 -0
- qrdqn-SpaceInvadersNoFrameskip-v4/system_info.txt +9 -0
- results.json +1 -1
- train_eval_metrics.zip +2 -2
README.md
CHANGED
@@ -6,7 +6,7 @@ tags:
|
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
8 |
model-index:
|
9 |
-
- name:
|
10 |
results:
|
11 |
- task:
|
12 |
type: reinforcement-learning
|
@@ -16,13 +16,13 @@ model-index:
|
|
16 |
type: SpaceInvadersNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
-
value:
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
-
# **
|
25 |
-
This is a trained model of a **
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
27 |
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
28 |
|
@@ -43,39 +43,31 @@ pip install rl_zoo3
|
|
43 |
|
44 |
```
|
45 |
# Download model and save it into the logs/ folder
|
46 |
-
python -m rl_zoo3.load_from_hub --algo
|
47 |
-
python -m rl_zoo3.enjoy --algo
|
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
|
53 |
-
python -m rl_zoo3.enjoy --algo
|
54 |
```
|
55 |
|
56 |
## Training (with the RL Zoo)
|
57 |
```
|
58 |
-
python -m rl_zoo3.train --algo
|
59 |
# Upload the model and generate video (when possible)
|
60 |
-
python -m rl_zoo3.push_to_hub --algo
|
61 |
```
|
62 |
|
63 |
## Hyperparameters
|
64 |
```python
|
65 |
-
OrderedDict([('
|
66 |
-
('buffer_size', 10000),
|
67 |
-
('env_wrapper',
|
68 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
69 |
-
('
|
70 |
-
('exploration_fraction', 0.1),
|
71 |
('frame_stack', 4),
|
72 |
-
('gradient_steps', 1),
|
73 |
-
('learning_rate', 0.001),
|
74 |
-
('learning_starts', 10000),
|
75 |
('n_timesteps', 1000000.0),
|
76 |
('optimize_memory_usage', False),
|
77 |
('policy', 'CnnPolicy'),
|
78 |
-
('target_update_interval', 1000),
|
79 |
-
('train_freq', 4),
|
80 |
('normalize', False)])
|
81 |
```
|
|
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
8 |
model-index:
|
9 |
+
- name: QRDQN
|
10 |
results:
|
11 |
- task:
|
12 |
type: reinforcement-learning
|
|
|
16 |
type: SpaceInvadersNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 660.00 +/- 181.16
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **QRDQN** Agent playing **SpaceInvadersNoFrameskip-v4**
|
25 |
+
This is a trained model of a **QRDQN** agent playing **SpaceInvadersNoFrameskip-v4**
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
27 |
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
28 |
|
|
|
43 |
|
44 |
```
|
45 |
# Download model and save it into the logs/ folder
|
46 |
+
python -m rl_zoo3.load_from_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -orga dylwil3 -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo qrdqn --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 qrdqn --env SpaceInvadersNoFrameskip-v4 -orga dylwil3 -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
54 |
```
|
55 |
|
56 |
## Training (with the RL Zoo)
|
57 |
```
|
58 |
+
python -m rl_zoo3.train --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
59 |
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo qrdqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga dylwil3
|
61 |
```
|
62 |
|
63 |
## Hyperparameters
|
64 |
```python
|
65 |
+
OrderedDict([('env_wrapper',
|
|
|
|
|
66 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
67 |
+
('exploration_fraction', 0.025),
|
|
|
68 |
('frame_stack', 4),
|
|
|
|
|
|
|
69 |
('n_timesteps', 1000000.0),
|
70 |
('optimize_memory_usage', False),
|
71 |
('policy', 'CnnPolicy'),
|
|
|
|
|
72 |
('normalize', False)])
|
73 |
```
|
args.yml
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - algo
|
3 |
-
-
|
4 |
- - conf_file
|
5 |
- null
|
6 |
- - device
|
@@ -54,7 +54,7 @@
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
-
-
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - algo
|
3 |
+
- qrdqn
|
4 |
- - conf_file
|
5 |
- null
|
6 |
- - device
|
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 1302513789
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
config.yml
CHANGED
@@ -1,29 +1,13 @@
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
-
- - -
|
3 |
-
- 64
|
4 |
-
- - buffer_size
|
5 |
-
- 10000
|
6 |
-
- - env_wrapper
|
7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
-
- - exploration_final_eps
|
9 |
-
- 0.01
|
10 |
- - exploration_fraction
|
11 |
-
- 0.
|
12 |
- - frame_stack
|
13 |
- 4
|
14 |
-
- - gradient_steps
|
15 |
-
- 1
|
16 |
-
- - learning_rate
|
17 |
-
- 0.001
|
18 |
-
- - learning_starts
|
19 |
-
- 10000
|
20 |
- - n_timesteps
|
21 |
- 1000000.0
|
22 |
- - optimize_memory_usage
|
23 |
- false
|
24 |
- - policy
|
25 |
- CnnPolicy
|
26 |
-
- - target_update_interval
|
27 |
-
- 1000
|
28 |
-
- - train_freq
|
29 |
-
- 4
|
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - env_wrapper
|
|
|
|
|
|
|
|
|
3 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
|
|
|
|
4 |
- - exploration_fraction
|
5 |
+
- 0.025
|
6 |
- - frame_stack
|
7 |
- 4
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
- - n_timesteps
|
9 |
- 1000000.0
|
10 |
- - optimize_memory_usage
|
11 |
- false
|
12 |
- - policy
|
13 |
- CnnPolicy
|
|
|
|
|
|
|
|
qrdqn-SpaceInvadersNoFrameskip-v4.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c638397eaef186e232e8c438e9bc87eeb5d2ee98c13f5f86a2d0f3647c8c746a
|
3 |
+
size 37018588
|
qrdqn-SpaceInvadersNoFrameskip-v4/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.0.0a5
|
qrdqn-SpaceInvadersNoFrameskip-v4/data
ADDED
The diff for this file is too large to render.
See raw diff
|
|
qrdqn-SpaceInvadersNoFrameskip-v4/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16874494e12990e12223112de191d4c45b987ec0732958ce560806469938d49d
|
3 |
+
size 18405963
|
qrdqn-SpaceInvadersNoFrameskip-v4/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e851bd2ca7822ef59b09505021c99a3a45cb8ec2d6984a380a9207ef6aae7d6b
|
3 |
+
size 18405545
|
qrdqn-SpaceInvadersNoFrameskip-v4/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
|
3 |
+
size 431
|
qrdqn-SpaceInvadersNoFrameskip-v4/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
|
2 |
+
- Python: 3.10.11
|
3 |
+
- Stable-Baselines3: 2.0.0a5
|
4 |
+
- PyTorch: 2.0.0+cu118
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.22.4
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
9 |
+
- OpenAI Gym: 0.26.2
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 660.0, "std_reward": 181.1629101113139, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-04-28T23:07:33.191456"}
|
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:a4e5066bfdb51f7c6753430e365afca3f5c0d96b45d5b6a21f3a282369b12468
|
3 |
+
size 6134
|