Initial commit
Browse files- README.md +20 -18
- args.yml +2 -2
- config.yml +18 -14
- 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 +2 -2
- dqn-SpaceInvadersNoFrameskip-v4/system_info.txt +5 -5
- replay.mp4 +2 -2
- 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 |
|
@@ -38,37 +38,39 @@ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
|
38 |
|
39 |
```
|
40 |
# Download model and save it into the logs/ folder
|
41 |
-
python -m rl_zoo3.load_from_hub --algo
|
42 |
-
python enjoy.py --algo
|
43 |
```
|
44 |
|
45 |
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
46 |
```
|
47 |
-
python -m rl_zoo3.load_from_hub --algo
|
48 |
-
rl_zoo3 enjoy --algo
|
49 |
```
|
50 |
|
51 |
## Training (with the RL Zoo)
|
52 |
```
|
53 |
-
python train.py --algo
|
54 |
# Upload the model and generate video (when possible)
|
55 |
-
python -m rl_zoo3.push_to_hub --algo
|
56 |
```
|
57 |
|
58 |
## Hyperparameters
|
59 |
```python
|
60 |
-
OrderedDict([('batch_size',
|
61 |
-
('
|
62 |
-
('ent_coef', 0.01),
|
63 |
('env_wrapper',
|
64 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
|
|
|
|
65 |
('frame_stack', 4),
|
66 |
-
('
|
67 |
-
('
|
68 |
-
('
|
69 |
-
('n_steps', 128),
|
70 |
('n_timesteps', 10000000.0),
|
|
|
71 |
('policy', 'CnnPolicy'),
|
72 |
-
('
|
|
|
73 |
('normalize', False)])
|
74 |
```
|
|
|
6 |
- reinforcement-learning
|
7 |
- stable-baselines3
|
8 |
model-index:
|
9 |
+
- name: DQN
|
10 |
results:
|
11 |
- task:
|
12 |
type: reinforcement-learning
|
|
|
16 |
type: SpaceInvadersNoFrameskip-v4
|
17 |
metrics:
|
18 |
- type: mean_reward
|
19 |
+
value: 892.50 +/- 340.74
|
20 |
name: mean_reward
|
21 |
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
|
25 |
+
This is a trained model of a **DQN** 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 |
|
|
|
38 |
|
39 |
```
|
40 |
# Download model and save it into the logs/ folder
|
41 |
+
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Roberto -f logs/
|
42 |
+
python enjoy.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
43 |
```
|
44 |
|
45 |
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
46 |
```
|
47 |
+
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Roberto -f logs/
|
48 |
+
rl_zoo3 enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
49 |
```
|
50 |
|
51 |
## Training (with the RL Zoo)
|
52 |
```
|
53 |
+
python train.py --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
|
54 |
# Upload the model and generate video (when possible)
|
55 |
+
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Roberto
|
56 |
```
|
57 |
|
58 |
## Hyperparameters
|
59 |
```python
|
60 |
+
OrderedDict([('batch_size', 32),
|
61 |
+
('buffer_size', 100000),
|
|
|
62 |
('env_wrapper',
|
63 |
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
|
64 |
+
('exploration_final_eps', 0.01),
|
65 |
+
('exploration_fraction', 0.1),
|
66 |
('frame_stack', 4),
|
67 |
+
('gradient_steps', 1),
|
68 |
+
('learning_rate', 0.0001),
|
69 |
+
('learning_starts', 100000),
|
|
|
70 |
('n_timesteps', 10000000.0),
|
71 |
+
('optimize_memory_usage', False),
|
72 |
('policy', 'CnnPolicy'),
|
73 |
+
('target_update_interval', 1000),
|
74 |
+
('train_freq', 4),
|
75 |
('normalize', False)])
|
76 |
```
|
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 |
+
- dqn
|
4 |
- - conf_file
|
5 |
- null
|
6 |
- - device
|
|
|
54 |
- - save_replay_buffer
|
55 |
- false
|
56 |
- - seed
|
57 |
+
- 1190980102
|
58 |
- - storage
|
59 |
- null
|
60 |
- - study_name
|
config.yml
CHANGED
@@ -1,25 +1,29 @@
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - batch_size
|
3 |
-
-
|
4 |
-
- -
|
5 |
-
-
|
6 |
-
- - ent_coef
|
7 |
-
- 0.01
|
8 |
- - env_wrapper
|
9 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
|
|
|
|
|
|
|
|
10 |
- - frame_stack
|
11 |
- 4
|
|
|
|
|
12 |
- - learning_rate
|
13 |
-
-
|
14 |
-
- -
|
15 |
-
-
|
16 |
-
- - n_epochs
|
17 |
-
- 4
|
18 |
-
- - n_steps
|
19 |
-
- 128
|
20 |
- - n_timesteps
|
21 |
- 10000000.0
|
|
|
|
|
22 |
- - policy
|
23 |
- CnnPolicy
|
24 |
-
- -
|
25 |
-
-
|
|
|
|
|
|
1 |
!!python/object/apply:collections.OrderedDict
|
2 |
- - - batch_size
|
3 |
+
- 32
|
4 |
+
- - buffer_size
|
5 |
+
- 100000
|
|
|
|
|
6 |
- - env_wrapper
|
7 |
- - stable_baselines3.common.atari_wrappers.AtariWrapper
|
8 |
+
- - exploration_final_eps
|
9 |
+
- 0.01
|
10 |
+
- - exploration_fraction
|
11 |
+
- 0.1
|
12 |
- - frame_stack
|
13 |
- 4
|
14 |
+
- - gradient_steps
|
15 |
+
- 1
|
16 |
- - learning_rate
|
17 |
+
- 0.0001
|
18 |
+
- - learning_starts
|
19 |
+
- 100000
|
|
|
|
|
|
|
|
|
20 |
- - n_timesteps
|
21 |
- 10000000.0
|
22 |
+
- - optimize_memory_usage
|
23 |
+
- false
|
24 |
- - policy
|
25 |
- CnnPolicy
|
26 |
+
- - target_update_interval
|
27 |
+
- 1000
|
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 sha256:7799bb75a0957ba4816da88b2f04eaaff09bd2dab5407643b47e94229530b500
|
3 |
+
size 27224904
|
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:ad841495214761f229b0f45b3914cbe83dea6bfa4a5f0f563197fcb8df95214f
|
3 |
+
size 13505419
|
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:fdeaf40f2bd414d341781ddaf39e1a4a94ce9e09dcb93d0e475f17c3d90385d3
|
3 |
+
size 13504745
|
dqn-SpaceInvadersNoFrameskip-v4/system_info.txt
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
OS: Linux-5.
|
2 |
-
Python: 3.
|
3 |
Stable-Baselines3: 1.6.2
|
4 |
-
PyTorch: 1.13.
|
5 |
-
GPU Enabled:
|
6 |
-
Numpy: 1.
|
7 |
Gym: 0.21.0
|
|
|
1 |
+
OS: Linux-5.15.0-56-generic-x86_64-with-glibc2.35 #62-Ubuntu SMP Tue Nov 22 19:54:14 UTC 2022
|
2 |
+
Python: 3.9.15
|
3 |
Stable-Baselines3: 1.6.2
|
4 |
+
PyTorch: 1.13.1+cu117
|
5 |
+
GPU Enabled: False
|
6 |
+
Numpy: 1.24.0
|
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 sha256:40a9f1812bd15d2fc97d7f87743d9093e2f64c994cea01c5945212b96d119541
|
3 |
+
size 195972
|
results.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"mean_reward":
|
|
|
1 |
+
{"mean_reward": 892.5, "std_reward": 340.74367198819704, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-12-24T17:16:22.255684"}
|
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 sha256:4b41fa0a29e21fab4b06e0f9a07bc5c3a2d3887a8976ec789a81a0dcf00730b2
|
3 |
+
size 135924
|