| behaviors: | |
| SnowballTarget: | |
| trainer_type: ppo | |
| hyperparameters: | |
| learning_rate: 0.0005 | |
| batch_size: 64 | |
| buffer_size: 1024 | |
| beta: 0.005 | |
| epsilon: 0.2 | |
| lambd: 0.95 | |
| num_epoch: 3 | |
| network_settings: | |
| hidden_units: 128 | |
| num_layers: 1 | |
| reward_signals: | |
| extrinsic: | |
| gamma: 0.99 | |
| strength: 1.0 | |