Results and code for cartpole

[kvfrans]

Writeup and code implementing random search, hill climbing, and policy gradient on the cartpole environment

[ilyasu123]

Nice work. Few comments:

• The first reference to eligibility "eligibility = tf.log(good_probabilities)" -- it's not really the eligibility until you multiply it by the advantage. I recommend calling it something else.
• The second reference to eligibility: "``` def policy_gradient():

  [not shown: policy gradient code from before]

  advantages = tf.placeholder("float",[None,1])

  insert the elementwise multiplication by advantages

  eligibility = tf.log(good_probabilities) * advantages

is hard to connect to the previous code.  In particular, it's not obvious that you differentiate eligibility, at least not form a shallow reading.   The second point is more important, and makes it possible to change the name of the first eligibility.   Basically, don't shy away form a bit of code duplication in the explanation to your solution.   Otherwise, it's good.

Let me know when it's done and I'll merge it.

[kvfrans]

Thanks for the feedback, I updated the post.