[Solved] CS5225 Project 1-Dynamic Programming

In this assignment, you will be asked to implement policy iteration and value iteration for the Frozen Lake environment from OpenAI Gym and play the game with the algorithms you implemented. This project will be completed in Python 3.

Hints

• Policy EvaluationPlease note that reward can be defined on (state), (state, action), (state, action, next_state). In this assignment, we define the reward on (state,action,next_state). The following pseudocode is the general method.