def evaluate_env()

in baselines/gail/gail-eval.py [0:0]

• 43 lines of code
• 6 McCabe index (conditional complexity)

def evaluate_env(env_name, seed, policy_hidden_size, stochastic, reuse, prefix):

    def get_checkpoint_dir(checkpoint_list, limit, prefix):
        for checkpoint in checkpoint_list:
            if ('limitation_'+str(limit) in checkpoint) and (prefix in checkpoint):
                return checkpoint
        return None

    def policy_fn(name, ob_space, ac_space, reuse=False):
        return mlp_policy.MlpPolicy(name=name, ob_space=ob_space, ac_space=ac_space,
                                    reuse=reuse, hid_size=policy_hidden_size, num_hid_layers=2)

    data_path = os.path.join('data', 'deterministic.trpo.' + env_name + '.0.00.npz')
    dataset = load_dataset(data_path)
    checkpoint_list = glob.glob(os.path.join('checkpoint', '*' + env_name + ".*"))
    log = {
        'traj_limitation': [],
        'upper_bound': [],
        'avg_ret': [],
        'avg_len': [],
        'normalized_ret': []
    }
    for i, limit in enumerate(CONFIG['traj_limitation']):
        # Do one evaluation
        upper_bound = sum(dataset.rets[:limit])/limit
        checkpoint_dir = get_checkpoint_dir(checkpoint_list, limit, prefix=prefix)
        checkpoint_path = tf.train.latest_checkpoint(checkpoint_dir)
        env = gym.make(env_name + '-v1')
        env.seed(seed)
        print('Trajectory limitation: {}, Load checkpoint: {}, '.format(limit, checkpoint_path))
        avg_len, avg_ret = run_mujoco.runner(env,
                                             policy_fn,
                                             checkpoint_path,
                                             timesteps_per_batch=1024,
                                             number_trajs=10,
                                             stochastic_policy=stochastic,
                                             reuse=((i != 0) or reuse))
        normalized_ret = avg_ret/upper_bound
        print('Upper bound: {}, evaluation returns: {}, normalized scores: {}'.format(
            upper_bound, avg_ret, normalized_ret))
        log['traj_limitation'].append(limit)
        log['upper_bound'].append(upper_bound)
        log['avg_ret'].append(avg_ret)
        log['avg_len'].append(avg_len)
        log['normalized_ret'].append(normalized_ret)
        env.close()
    return log