MattStammers
commited on
Commit
•
f906323
1
Parent(s):
cec0753
Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,7 @@ tags:
|
|
5 |
- reinforcement-learning
|
6 |
- sample-factory
|
7 |
model-index:
|
8 |
-
- name:
|
9 |
results:
|
10 |
- task:
|
11 |
type: reinforcement-learning
|
@@ -20,7 +20,7 @@ model-index:
|
|
20 |
verified: false
|
21 |
---
|
22 |
|
23 |
-
A(n) **
|
24 |
|
25 |
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
|
26 |
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
|
@@ -30,7 +30,7 @@ Documentation for how to use Sample-Factory can be found at https://www.samplefa
|
|
30 |
|
31 |
After installing Sample-Factory, download the model with:
|
32 |
```
|
33 |
-
python -m sample_factory.huggingface.load_from_hub -r MattStammers/
|
34 |
```
|
35 |
|
36 |
|
@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r MattStammers/atqc-mujoco-s
|
|
38 |
|
39 |
To run the model after download, use the `enjoy` script corresponding to this environment:
|
40 |
```
|
41 |
-
python -m sf_examples.mujoco.enjoy_mujoco --algo=
|
42 |
```
|
43 |
|
44 |
|
@@ -49,7 +49,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
|
|
49 |
|
50 |
To continue training with this model, use the `train` script corresponding to this environment:
|
51 |
```
|
52 |
-
python -m sf_examples.mujoco.train_mujoco --algo=
|
53 |
```
|
54 |
|
55 |
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
|
|
5 |
- reinforcement-learning
|
6 |
- sample-factory
|
7 |
model-index:
|
8 |
+
- name: APPO
|
9 |
results:
|
10 |
- task:
|
11 |
type: reinforcement-learning
|
|
|
20 |
verified: false
|
21 |
---
|
22 |
|
23 |
+
A(n) **APPO** model trained on the **mujoco_standup** environment.
|
24 |
|
25 |
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
|
26 |
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
|
|
|
30 |
|
31 |
After installing Sample-Factory, download the model with:
|
32 |
```
|
33 |
+
python -m sample_factory.huggingface.load_from_hub -r MattStammers/appo-mujoco-standup
|
34 |
```
|
35 |
|
36 |
|
|
|
38 |
|
39 |
To run the model after download, use the `enjoy` script corresponding to this environment:
|
40 |
```
|
41 |
+
python -m sf_examples.mujoco.enjoy_mujoco --algo=APPO --env=mujoco_standup --train_dir=./train_dir --experiment=appo-mujoco-standup
|
42 |
```
|
43 |
|
44 |
|
|
|
49 |
|
50 |
To continue training with this model, use the `train` script corresponding to this environment:
|
51 |
```
|
52 |
+
python -m sf_examples.mujoco.train_mujoco --algo=APPO --env=mujoco_standup --train_dir=./train_dir --experiment=appo-mujoco-standup --restart_behavior=resume --train_for_env_steps=10000000000
|
53 |
```
|
54 |
|
55 |
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|