error in compute target q values

[hejia-zhang]

        target_q_batch = to_tensor(reward_batch) + \
            self.discount*to_tensor(terminal_batch.astype(np.float))*next_q_values

I think it should be

        target_q_batch = to_tensor(reward_batch) + \
            self.discount*to_tensor(1.0 - terminal_batch.astype(np.float))*next_q_values

[abalakrishna123]

yeah... that does seem like it would be the case

[songanz]

I think in the memory.py, he has:

    for e in experiences:
        state0_batch.append(e.state0)
        state1_batch.append(e.state1)
        reward_batch.append(e.reward)
        action_batch.append(e.action)
        terminal1_batch.append(0. if e.terminal1 else 1.)