dqn_feature.py 文件源码

def meanQvalue(Q, samples): 
    xp = Q.xp
    s = np.ndarray(shape=(minibatch_size, STATE_LENGTH, FRAME_WIDTH, FRAME_HEIGHT), dtype=np.float32)
    a = np.asarray([sample[1] for sample in samples], dtype=np.int32)

    for i in xrange(minibatch_size):
        s[i] = samples[i][0]

    # to gpu if available
    s = xp.asarray(s)
    a = xp.asarray(a)

    # Prediction: Q(s,a)
    y = F.select_item(Q(s), a)
    mean_Q = (F.sum(y)/minibatch_size).data
    return mean_Q