7327bc3aa7a0e66168a84380edbd1e74a5a16355,ch04/02_frozenlake_naive.py,,,#,90

Before Change

        loss_v.backward()
        optimizer.step()
        print("%d: loss=%.3f, reward_mean=%.1f, reward_bound=%.1f" % (
            iter_no, loss_v.data[0], reward_m, reward_b))
        writer.add_scalar("loss", loss_v.data[0], iter_no)
        writer.add_scalar("reward_bound", reward_b, iter_no)
        writer.add_scalar("reward_mean", reward_m, iter_no)
        if reward_m > 0.8:

After Change

        obs_v, acts_v, reward_b, reward_m = filter_batch(batch, PERCENTILE)
        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=%.1f, reward_bound=%.1f" % (
            iter_no, loss_v.item(), reward_m, reward_b))
        writer.add_scalar("loss", loss_v.item(), iter_no)
        writer.add_scalar("reward_bound", reward_b, iter_no)
        writer.add_scalar("reward_mean", reward_m, iter_no)
        if reward_m > 0.8:

Instances