Deep Reinforcement Learning Readings

  1. Spend at least 45 minutes studying this paper. (Use a clock. No guessing. If you finish early, spend the remaining time meditating on it, empirically validating it, studying papers it cites, or studying papers that cite it. If you find this paper interesting, please also note that you are not limited to spending only 45 minutes with it. Studying is good.)


  2. Spend at least 45 minutes studying this paper. In particular, please focus mostly on trying to understand the equations. (The prose does not generally matter. It is just there to help you understand the equations.)


  3. Spend at least 45 minutes studying this paper. Focus on the A3Q algorithm. In particular, please focus mostly on trying to understand the equations.


  4. (Optional) We will also briefly discuss this paper. I recommend that you read it.


  5. Send an e-mail to the instructor with the following message:
    I have completed assignment 2.