new_step_info.current_all_brain_info[brain_name],
new_step_info.brain_name_to_action_info[brain_name].outputs,
)
trainer_mock.clear_update_buffer.assert_called_once()
trainer_mock.advance.assert_called_once()
trainer.parameters["time_horizon"]
if "time_horizon" in trainer.parameters
else None,
trainer.summary_path,
self.managers[name] = agent_manager