Get Policy using Value Iteration and Policy Iteration Algorithm
The goal of this project is to get familiar with OpenAI Gym, implement value iteration and policy iteration.
Problem Description OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents everything from walking to playing games like Pong or Pinball. For more information visit https://gym.openai.com.
Frozen Lake is an environment where the agent controls the movement of a character in a grid world. Some tiles of the grid are walkable, and others lead to the agent falling into the water. Additionally, the movement direction of the agent is uncertain and only partially depends on the chosen direction. The agent is rewarded for finding a walkable path to a goal tile. For more information please visit https://gym.openai.com/envs/FrozenLake8x8-v0/.