Reinforcement Learning
ml-agents
TensorBoard
ONNX
Chinese
ML-Agents-Huggy
unity-ml-agents
deep-reinforcement-learning
Instructions to use wefio/ppo-Huggy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ml-agents
How to use wefio/ppo-Huggy with ml-agents:
mlagents-load-from-hf --repo-id="wefio/ppo-Huggy" --local-dir="./downloads"
- Notebooks
- Google Colab
- Kaggle
Download config.json from wefio/ppo-Huggy: direct link, hf CLI and curl.
- Browser
- Download file 598 Bytes
-
https://huggingface.co/wefio/ppo-Huggy/resolve/main/config.json
- Command line
-
hf download hf://wefio/ppo-Huggy/config.json
-
curl -L -o config.json https://huggingface.co/wefio/ppo-Huggy/resolve/main/config.json
598 Bytes
| {"behaviors": {"Huggy": {"trainer_type": "ppo", "threaded": true, "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear"}, "curiosity": {"strength": 0.01, "gamma": 0.995}, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0}}, "checkpoint_interval": 200000, "keep_checkpoints": 15, "max_steps": "2e6", "time_horizon": 1000, "summary_freq": 50000}}} |