reinforcement_q_learning.py 文件源码

def plot_durations():
    plt.figure(2)
    plt.clf()
    durations_t = torch.FloatTensor(episode_durations)
    plt.title('Training...')
    plt.xlabel('Episode')
    plt.ylabel('Duration')
    plt.plot(durations_t.numpy())
    # Take 100 episode averages and plot them too
    if len(durations_t) >= 100:
        means = durations_t.unfold(0, 100, 1).mean(1).view(-1)
        means = torch.cat((torch.zeros(99), means))
        plt.plot(means.numpy())

    plt.pause(0.001)  # pause a bit so that plots are updated
    if is_ipython:
        display.clear_output(wait=True)
        display.display(plt.gcf())


######################################################################
# Training loop
# ^^^^^^^^^^^^^
#
# Finally, the code for training our model.
#
# Here, you can find an ``optimize_model`` function that performs a
# single step of the optimization. It first samples a batch, concatenates
# all the tensors into a single one, computes :math:`Q(s_t, a_t)` and
# :math:`V(s_{t+1}) = \max_a Q(s_{t+1}, a)`, and combines them into our
# loss. By defition we set :math:`V(s) = 0` if :math:`s` is a terminal
# state.