Commit
•
cd1d812
1
Parent(s):
6c052b9
Upload folder using huggingface_hub
Browse files- README.md +21 -29
- hyperparameters.json +1 -0
- model.pt +3 -0
- replay.mp4 +0 -0
- results.json +1 -0
README.md
CHANGED
@@ -1,35 +1,27 @@
|
|
1 |
---
|
2 |
-
library_name: ml-agents
|
3 |
tags:
|
4 |
-
-
|
5 |
-
-
|
6 |
- reinforcement-learning
|
7 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
-
# **
|
11 |
-
This is a trained model of a **
|
12 |
-
|
13 |
-
|
14 |
-
## Usage (with ML-Agents)
|
15 |
-
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
|
16 |
-
|
17 |
-
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
|
18 |
-
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
|
19 |
-
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
|
20 |
-
- A *longer tutorial* to understand how works ML-Agents:
|
21 |
-
https://huggingface.co/learn/deep-rl-course/unit5/introduction
|
22 |
-
|
23 |
-
### Resume the training
|
24 |
-
```bash
|
25 |
-
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
|
26 |
-
```
|
27 |
-
|
28 |
-
### Watch your Agent play
|
29 |
-
You can watch your agent **playing directly in your browser**
|
30 |
-
|
31 |
-
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
|
32 |
-
2. Step 1: Find your model_id: JiajingChen/9
|
33 |
-
3. Step 2: Select your *.nn /*.onnx file
|
34 |
-
4. Click on Watch the agent play 👀
|
35 |
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
+
- Pixelcopter-PLE-v0
|
4 |
+
- reinforce
|
5 |
- reinforcement-learning
|
6 |
+
- custom-implementation
|
7 |
+
- deep-rl-class
|
8 |
+
model-index:
|
9 |
+
- name: '9'
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: Pixelcopter-PLE-v0
|
16 |
+
type: Pixelcopter-PLE-v0
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 44.30 +/- 41.50
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
---
|
23 |
|
24 |
+
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
|
25 |
+
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
|
26 |
+
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
|
hyperparameters.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
|
model.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6390d496559de0d1b79b5aa54ae740468974399d119913e299f54d228962948b
|
3 |
+
size 39668
|
replay.mp4
ADDED
Binary file (23.4 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 44.3, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-16T00:05:05.871217"}
|