Final Project (Phase I) Report

Describe in detail the algorithm(s) given in the paper(s) you have chosen, that provides a solution to the stated autonomous driving problem. Indicate what if any theoretical error bounds, guarantees are proved. What is the loss function of the problem? Additionally analyze the data experiments on this particular driving environment, and comparisons that have been performed. Thereby summarize all you learned from the paper(s) and the advantage and disadvantage of the method proposed in the paper(s).

Justify/show if the result stated in the paper can be reproduced using the code repo provided. What is the setup of state, action, policy and reward in the code repo.

Describe how you would extend/improve the existing solution under your own idea. If you wish to setup the environment differently, what are the changes? In addition, propose an experimental plan.