evaluator.py 文件源码

def __init__(self, agent, env, n_runs, eval_interval,
                 outdir, max_episode_len=None, explorer=None,
                 step_offset=0, logger=None):
        self.agent = agent
        self.env = env
        self.max_score = np.finfo(np.float32).min
        self.start_time = time.time()
        self.n_runs = n_runs
        self.eval_interval = eval_interval
        self.outdir = outdir
        self.max_episode_len = max_episode_len
        self.explorer = explorer
        self.step_offset = step_offset
        self.prev_eval_t = (self.step_offset -
                            self.step_offset % self.eval_interval)
        self.logger = logger or logging.getLogger(__name__)

        # Write a header line first
        with open(os.path.join(self.outdir, 'scores.txt'), 'w') as f:
            custom_columns = tuple(t[0] for t in self.agent.get_statistics())
            column_names = _basic_columns + custom_columns
            print('\t'.join(column_names), file=f)