7327bc3aa7a0e66168a84380edbd1e74a5a16355,ch04/04_frozenlake_nonslippery.py,,,#,93

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)

After Change

        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)

Instances