ppo Agent playing SnowballTarget

This is a trained model of a ppo agent playing SnowballTarget using the Unity ML-Agents Library.

Usage (with ML-Agents)

The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/

Watch the Agent play

You can watch the agent playing directly in your browser

1. Go to https://huggingface.co/spaces/ThomasSimonini/ML-Agents-SnowballTarget
2. Step 1: Find the model_id: Francesco-A/ppo-SnowballTarget-v1
3. Step 2: Select the .nn /.onnx file
4. Click on Watch the agent play

Training hyperparameters

behaviors:
  SnowballTarget:
    trainer_type: ppo
    summary_freq: 10000
    keep_checkpoints: 10
    checkpoint_interval: 55000
    max_steps: 250000
    time_horizon: 64
    threaded: true
    hyperparameters:
      learning_rate: 0.0003
      learning_rate_schedule: linear
      batch_size: 128
      buffer_size: 2048
      beta: 0.005
      epsilon: 0.2
      lambd: 0.95
      num_epoch: 3
    network_settings:
      normalize: false
      hidden_units: 256
      num_layers: 2
      vis_encode_type: simple
    reward_signals:
      extrinsic:
        gamma: 0.99
        strength: 1.0

Training details