| behaviors: | |
| SoccerTwos: | |
| trainer_type: poca | |
| hyperparameters: | |
| batch_size: 2048 | |
| buffer_size: 20480 | |
| learning_rate: 0.0003 | |
| beta: 0.005 | |
| epsilon: 0.2 | |
| lambd: 0.95 | |
| num_epoch: 3 | |
| learning_rate_schedule: constant | |
| beta_schedule: constant | |
| epsilon_schedule: constant | |
| checkpoint_interval: 500000 | |
| network_settings: | |
| normalize: false | |
| hidden_units: 512 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| memory: null | |
| goal_conditioning_type: hyper | |
| deterministic: false | |
| reward_signals: | |
| extrinsic: | |
| gamma: 0.99 | |
| strength: 1.0 | |
| network_settings: | |
| normalize: false | |
| hidden_units: 128 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| memory: null | |
| goal_conditioning_type: hyper | |
| deterministic: false | |
| keep_checkpoints: 5 | |
| max_steps: 10500000 | |
| time_horizon: 1000 | |
| summary_freq: 10000 | |
| self_play: | |
| save_steps: 50000 | |
| team_change: 200000 | |
| swap_steps: 2000 | |
| window: 10 | |
| play_against_latest_model_ratio: 0.5 | |
| initial_elo: 1200.0 | |