• Introduction
The goal of this assignment is to do experiments with Monte-Carlo(MC) Learn-ing and Temporal-Di erence(TD) Learning. MC and TD methods learn directly from episodes of experience without knowledge of MDP model. TD method can learn after every step, while MC method requires a full episode to update value evaluation. Your goal is to implement MC and TD methods and test them in the small gridworld.
• Small Gridworld
Figure 1: Gridworld
As shown in Fig.1, each grid in the gridwold represents a certain state. Let st denotes the state at grid t. Hence the state space can be denoted as S = fstjt 2 0; ::; 35g. S1 and S35 are terminal states, where the others are non-terminal states and can move one grid to north, east, south and west. Hence the action space is A = fn; e; s; wg. Note that actions leading out of the grid leave state unchanged. Each movement get a reward of -1 until the terminal state is reached.
• Experiment Requirments
Programming language: python3
You should implement both rst-visit and every-visit MC method and TD(0) to evaluate state value in small grid world.
• Report and Submission
Your reports and source les (.py) should be compressed and named after \studentID+name".
2
The les should be submitted on Canvas before Apr. 10, 2020.
3
