Solving OpenAI FrozenLake environment with -Policy Iteration and -Value Iteration algorithms.
:focal(481x563:482x564)/https://public-media.smithsonianmag.com/filer/bb/27/bb27e41a-e318-4501-9b06-e1b21f978b24/nmp7124.jpg)
It was part of www.theschool.ai MOVE 37 course
The goal is to control movement of a character to walk from start point to end point and avoiding holes in the ice
- Numpy
- OpenAI gym
Repo contains two files each with differend method of solving the problem