Repository for the second homework for the Reinforcement Learning course of the M.Sc in Artificial Intelligence and Robotics at Sapienza University.
- SARSA(
$\lambda$ ) - RBF encoder
- TD(
$\lambda$ )
- document.pdf, file where are listed the tasks to perform.
- Theory.pdf, file containing the responses to the theory's questions.
-
assignment2 folder, that contains the code files:
-
ilqr folder, code files and trained model of the exercise about RBF encoder and TD(
$\lambda$ ) algorithm. -
policy_iteration folder, code files of the SARSA(
$\lambda$ ) algorithm.
-
ilqr folder, code files and trained model of the exercise about RBF encoder and TD(