| behaviors: | |
| Pyramids: | |
| trainer_type: ppo | |
| hyperparameters: | |
| batch_size: 128 | |
| buffer_size: 2048 | |
| learning_rate: 0.0003 | |
| beta: 0.01 | |
| epsilon: 0.2 | |
| lambd: 0.95 | |
| num_epoch: 3 | |
| learning_rate_schedule: linear | |
| network_settings: | |
| normalize: false | |
| hidden_units: 128 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| reward_signals: | |
| extrinsic: | |
| gamma: 0.99 | |
| strength: 1.0 | |
| rnd: | |
| gamma: 0.99 | |
| strength: 0.01 | |
| network_settings: | |
| hidden_units: 64 | |
| num_layers: 3 | |
| learning_rate: 0.0001 | |
| keep_checkpoints: 2 | |
| max_steps: 30000 | |
| time_horizon: 128 | |
| summary_freq: 2000 | |
| checkpoint_interval: 10000 | |