behaviors: 3DBall: // <= こちらの名前と Behavior が一致していないと、ゲーム起動時にPythonでエラーが発生して停止する trainer_type: ppo hyperparameters: batch_size: 10 buffer_size: 100 learning_rate: 0.0003 beta: 0.005 epsilon: 0.2 lambd: 0.99 num_epoch: 3 learning_rate_schedule: linear network_settings: normalize: true hidden_units: 128 num_layers: 2 vis_encode_type: simple reward_signals: extrinsic: gamma: 0.99 strength: 1.0 keep_checkpoints: 5 checkpoint_interval: 500000 max_steps: 500000 time_horizon: 64 summary_freq: 1000 threaded: true