electricwapiti
commited on
Commit
•
2495340
1
Parent(s):
d5b504d
Update README.md
Browse files
README.md
CHANGED
@@ -1,27 +1,35 @@
|
|
1 |
-
---
|
2 |
-
library_name: stable-baselines3
|
3 |
-
tags:
|
4 |
-
- SpaceInvadersNoFrameskip-v4
|
5 |
-
- deep-reinforcement-learning
|
6 |
-
- reinforcement-learning
|
7 |
-
- stable-baselines3
|
8 |
-
model-index:
|
9 |
-
- name: DQN
|
10 |
-
results:
|
11 |
-
- task:
|
12 |
-
type: reinforcement-learning
|
13 |
-
name: reinforcement-learning
|
14 |
-
dataset:
|
15 |
-
name: SpaceInvadersNoFrameskip-v4
|
16 |
-
type: SpaceInvadersNoFrameskip-v4
|
17 |
-
metrics:
|
18 |
-
- type: mean_reward
|
19 |
-
value: 148.00 +/- 49.31
|
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).
|
@@ -83,4 +91,4 @@ OrderedDict([('batch_size', 32),
|
|
83 |
# Environment Arguments
|
84 |
```python
|
85 |
{'render_mode': 'rgb_array'}
|
86 |
-
```
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- SpaceInvadersNoFrameskip-v4
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: DQN
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: SpaceInvadersNoFrameskip-v4
|
16 |
+
type: SpaceInvadersNoFrameskip-v4
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 148.00 +/- 49.31
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
license: wtfpl
|
23 |
+
---
|
24 |
|
25 |
+
# **8/15-16/24 : I am curently trying to improve the DQN algorithm**
|
26 |
+
# **to reach a score above 200 within a limited processing time**
|
27 |
+
# **(1 hr GPU, 3 hrs CPU, max 500000 timesteps).**
|
28 |
+
# **I am open to hyperparameters/referrals/suggestions! Thanks :)**
|
29 |
+
|
30 |
+
<br><br><br><br><br><br><br><br><br><br>
|
31 |
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
|
32 |
+
|
33 |
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
|
34 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
35 |
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
|
|
91 |
# Environment Arguments
|
92 |
```python
|
93 |
{'render_mode': 'rgb_array'}
|
94 |
+
```
|