7327bc3aa7a0e66168a84380edbd1e74a5a16355,ch04/02_frozenlake_naive.py,,iterate_batches,#,47

Before Change

    obs = env.reset()
    sm = nn.Softmax(dim=1)
    while True:
        obs_v = Variable(torch.from_numpy(np.array([obs])))
        act_probs_v = sm(net(obs_v))
        act_probs = act_probs_v.data.numpy()[0]
        action = np.random.choice(len(act_probs), p=act_probs)
        next_obs, reward, is_done, _ = env.step(action)
        episode_reward += reward
        episode_steps.append(EpisodeStep(observation=obs, action=action))

After Change

    obs = env.reset()
    sm = nn.Softmax(dim=1)
    while True:
        obs_v = torch.FloatTensor([obs])
        act_probs_v = sm(net(obs_v))
        act_probs = act_probs_v.data.numpy()[0]
        action = np.random.choice(len(act_probs), p=act_probs)
        next_obs, reward, is_done, _ = env.step(action)
        episode_reward += reward
        episode_steps.append(EpisodeStep(observation=obs, action=action))

Instances