| {"behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 102400, "learning_rate": 0.0005, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "learning_rate_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 384, "num_layers": 2, "vis_encode_type": "simple"}, "reward_signals": {"extrinsic": {"gamma": 0.97, "strength": 1.0}}, "keep_checkpoints": 5, "max_steps": 10000000, "time_horizon": 1512, "summary_freq": 20000, "self_play": {"save_steps": 75000, "team_change": 300000, "swap_steps": 30000, "window": 17, "play_against_latest_model_ratio": 0.6, "initial_elo": 1200.0}}}} |