| behaviors: | |
| Basic: | |
| trainer_type: sac | |
| hyperparameters: | |
| learning_rate: 0.0003 | |
| learning_rate_schedule: constant | |
| batch_size: 64 | |
| buffer_size: 50000 | |
| buffer_init_steps: 0 | |
| tau: 0.005 | |
| steps_per_update: 10.0 | |
| save_replay_buffer: false | |
| init_entcoef: 0.01 | |
| reward_signal_steps_per_update: 10.0 | |
| network_settings: | |
| normalize: false | |
| hidden_units: 20 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| reward_signals: | |
| extrinsic: | |
| gamma: 0.99 | |
| strength: 1.0 | |
| keep_checkpoints: 5 | |
| max_steps: 500000 | |
| time_horizon: 10 | |
| summary_freq: 2000 | |