2021 RL Final Project

Final project for the course of Reinforcement Learning 2020/2021.

Student: Alessandro Lambertini Mat: 1938390;

Student: Denise Landini Mat: 1938388;

📝 Assignment

1. Reimplement the Paper Link 🔗 (Github page of the paper Link 🔗)
   • [RL]implementation.ipynb Open In Collab 🔗
2. Improving the paper in large and complex environments.
   • [RL]experiments.ipynb Open In Collab 🔗

📜 Report

• report Link 🔗

  In this file you can read more about the code and the result of the project.

💯 Final score:

Score: 30L/30

🙋 Info

for any doubt or clarification contact me on:

• send me an email at: lambertini.1938390@studenti.uniroma1.it
• send me a DM on instagram Link 🔗

🎞️ Snapshots

Carpole Enviroment with Belief Map

Video of one epoch of Carpole Enviroment

Taxi Enviroment with Belief Map

Our Enviroment with Belief Map

Video of one epoch of Our Enviroment