|
|
--- |
|
|
license: mit |
|
|
pipeline_tag: reinforcement-learning |
|
|
library_name: ml-agents |
|
|
tags: |
|
|
- BVS.1 |
|
|
- BVS |
|
|
- deep-reinforcement-learning |
|
|
- ML-Agents |
|
|
--- |
|
|
# ppo Agent playing BVS V1 |
|
|
|
|
|
|
|
|
This is a trained model of a ppo agent playing [BroVSister](https://huggingface.co/spaces/RafaelJaime/BroVSister) using the [Godot rl agents](https://github.com/edbeeching/godot_rl_agents) using the example of stable_baselines3. |
|
|
|
|
|
## Resume the training |
|
|
|
|
|
```bash |
|
|
python stable_baselines3_example.py --timesteps=100_000 --onnx_export_path=model.onnx |
|
|
--save_model_path=model.zip --save_checkpoint_frequency=20_000 --experiment_name=exp1 |
|
|
``` |
|
|
|
|
|
### Watch your Agent play |
|
|
|
|
|
You can watch your agent **playing directly in your browser** |
|
|
|
|
|
1. Go to [BVS Huggingface space](https://huggingface.co/spaces/RafaelJaime/BroVSister) and go to character select menu |
|
|
2. Step 1: Find your model_id: RafaelJaime/*yourBVSmodelname* |
|
|
3. Step 2: Select your *.nn /*.onnx file |
|
|
4. Click on Watch the agent play 👀 |
