<p>In <a href="https://github.com/mlpack/mlpack/pull/686#discussion_r71423373">src/mlpack/methods/ne/tasks.hpp</a>:</p>
<pre style='color:#555'>&gt; +        genome.Output(output);
&gt; +
&gt; +        double action = output[0];
&gt; +        if (output[0] &lt; 0.5) {
&gt; +          action = -1;
&gt; +        } else {
&gt; +          action = 1;
&gt; +        }
&gt; +        
&gt; +        Action(action, x, x_dot, theta, theta_dot);
&gt; +        fitness += 1;
&gt; +        if (abs(x)&gt;=track_limit || abs(theta)&gt;=theta_limit) break;
&gt; +      }
&gt; +    }
&gt; +
&gt; +    return (1.0 / fitness);
</pre>
<p>Do you think it's a good idea to normalize the fitness?</p>

<p>return = 1 - double(fitness) / (num_trial * num_step);</p>

<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">&mdash;<br />You are receiving this because you are subscribed to this thread.<br />Reply to this email directly, <a href="https://github.com/mlpack/mlpack/pull/686/files/66b0f4171ab0c6810cf3058e653e48d18c4913be#r71423373">view it on GitHub</a>, or <a href="https://github.com/notifications/unsubscribe-auth/AJ4bFLdoDTowRgQWLJKzeIWxE6H01CVjks5qXTxGgaJpZM4IwJa6">mute the thread</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFM8dt_OXsSA_xt37_NOx-8k4lgJaks5qXTxGgaJpZM4IwJa6.gif" width="1" /></p>
<div itemscope itemtype="http://schema.org/EmailMessage">
<div itemprop="action" itemscope itemtype="http://schema.org/ViewAction">
  <link itemprop="url" href="https://github.com/mlpack/mlpack/pull/686/files/66b0f4171ab0c6810cf3058e653e48d18c4913be#r71423373"></link>
  <meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>