Exercise 6: Approximation in value space

Paper Exercises

In this exercise we will discuss

• Cost function approximation
• Convergence of gradient descent methods
• Modelling a chess engine using dynamic programming (with multistep lookahead)
• Online vs. offline implementation and terminal cost approximation

Paper exercises and solutions can be found in the exercise compendium.

It is recommended that you complete this paper exercise before moving on to the computer exercise.

Computer Exercises

• Rocket Landing: Second order polynomial Value function