def evaluate()

in pyhanabi/eval.py [0:0]

• 39 lines of code
• 13 McCabe index (conditional complexity)

def evaluate(agents, num_game, seed, bomb, eps, sad, *, hand_size=5, runners=None, device="cuda:0"):
    """
    evaluate agents as long as they have a "act" function
    """
    assert agents is None or runners is None
    if agents is not None:
        runners = [rela.BatchRunner(agent, device, 1000, ["act"]) for agent in agents]
    num_player = len(runners)

    context = rela.Context()
    games = create_envs(
        num_game,
        seed,
        num_player,
        hand_size,
        bomb,
        [eps],
        -1,
        sad,
        False,
        False,
    )

    for g in games:
        env = hanalearn.HanabiVecEnv()
        env.append(g)
        actors = []
        for i in range(num_player):
            actors.append(rela.R2D2Actor(runners[i], 1))
        thread = hanalearn.HanabiThreadLoop(actors, env, True)
        context.push_env_thread(thread)

    for runner in runners:
        runner.start()

    context.start()
    while not context.terminated():
        time.sleep(0.5)
    context.terminate()
    while not context.terminated():
        time.sleep(0.5)

    for runner in runners:
        runner.stop()

    scores = [g.last_score() for g in games]
    num_perfect = np.sum([1 for s in scores if s == 25])
    return np.mean(scores), num_perfect / len(scores), scores, num_perfect