Below are a number of practice questions for the midterm exam. You
should take a look at them to get an idea what kind of questions I will
ask. 
<p>

NOTE: This is not a comprehensive list of topics, or a study
guide. These are examples; the actual exam questions will be
very similar to these. Use the lecture notes (i.e. presentation
slides) as the study guide.
<p>

To get the most benefit out of these examples, try to answer them first
yourself. Then go to the slides/readings to make sure you got it
right. Then think of other similar questions yourself!

<p>
EVOLUTION BASICS<br>
How can population-based search explore more effectively than
hill-climbing based approaches?

<p>
NEURAL NETWORK BASICS<BR>
What is the main idea behind learning by gradient descent?

<p>
NEUROEVOLUTION BASICS<BR>
Name two advantages of neuroevolution over value-function-based
reinforcement learning. 

<p>
INDIRECT ENCODINGS<BR>
What is the difference between Lamarckian evolution and the Baldwin
effect?

<p>
DIVERSITY<BR>
What is the difference between genetic diversity and behavioral
diversity? 

<p>
BEHAVIOR: CONTROL<BR>
Describe one idea to help generalize control to new situations.

<p>
BEHAVIOR: STRATEGY<BR>
Why is it difficult to evolve cognitive behaviors?

<p>
BEHAVIOR: DECISION-MAKING<BR>
Why is it useful to have a surrogate model of the world when learning
decision strategies?

<p>
COLLECTIVE SYSTEMS<BR>
Describe one idea for encouraging true progress towards better
solutions in competitive coevolution.