We have learned several learning algorithms $($e$.$g$.,$ Q$-$learning, Monte Carlo, dynamic

programming, double Q$-$learning, TD$,$ SARSA and others$).$

You are free to pick up any one algorithm and implement on a grid world goal searching

problem.

Choose one algorithm you are going to implement and provide your complete pseudo code.

Design your own grid world example $($should be bigger than $3^{**}2)$ and with obstacles.

Show your goal searching process with step$-$to$-$go curve, sum of squared error and$/$or

theoretical value table

Please submit the report$/$code

Please include following five sections.

Introduction and Background $($aims$/$motivation$,$ review$/$research$)$

Project Specification $($goals$/$objective$,$ problem design, and expected solution$)$

Implementation $($evaluation$,$ such as case studies$)$

Summary $($conclusions$)$

Please include your pseudocode, problem statement, input sequence, and output in the report.

Please give your derived $($theoretical$)$ solution of $V$ table or $Q$ table for your problem.

Visualizing the graphs or providing the tables$/$graphs in the report is suggested