7327bc3aa7a0e66168a84380edbd1e74a5a16355,ch04/03_frozenlake_tweaked.py,,,#,91

Before Change

        full_batch, obs, acts, reward_bound = filter_batch(full_batch + batch, PERCENTILE)
        if not full_batch:
            continue
        obs_v = Variable(torch.from_numpy(np.array(obs)))
        acts_v = Variable(torch.from_numpy(np.array(acts)))
        full_batch = full_batch[-500:]

        optimizer.zero_grad()
        action_scores_v = net(obs_v)
        loss_v = objective(action_scores_v, acts_v)
        loss_v.backward()
        optimizer.step()
        print("%d: loss=%.3f, reward_mean=%.3f, reward_bound=%.3f, batch=%d" % (
            iter_no, loss_v.data[0], reward_mean, reward_bound, len(full_batch)))
        writer.add_scalar("loss", loss_v.data[0], iter_no)
        writer.add_scalar("reward_mean", reward_mean, iter_no)
        writer.add_scalar("reward_bound", reward_bound, iter_no)
        if reward_mean > 0.8:

After Change

        full_batch, obs, acts, reward_bound = filter_batch(full_batch + batch, PERCENTILE)
        if not full_batch:
            continue
        obs_v = torch.FloatTensor(obs)
        acts_v = torch.LongTensor(acts)
        full_batch = full_batch[-500:]

        optimizer.zero_grad()
        action_scores_v = net(obs_v)
        loss_v = objective(action_scores_v, acts_v)
        loss_v.backward()
        optimizer.step()
        print("%d: loss=%.3f, reward_mean=%.3f, reward_bound=%.3f, batch=%d" % (
            iter_no, loss_v.item(), reward_mean, reward_bound, len(full_batch)))
        writer.add_scalar("loss", loss_v.item(), iter_no)
        writer.add_scalar("reward_mean", reward_mean, iter_no)
        writer.add_scalar("reward_bound", reward_bound, iter_no)
        if reward_mean > 0.8:

Instances