This repository contains the final submission for the Project done for the course EE5611: Machine Learning for Wireless Networks at IIT Hyderabad.

This work is an implementation of the paper:

[Shangxing Wang , Hanpeng Liu, Pedro Henrique Gomes, and Bhaskar Krishnamachari, “Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks” IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, VOL. 4, NO. 2, JUNE 2018] (https://ieeexplore.ieee.org/document/8303773)

1. Tensorflow-2.0.alpha-0
2. matplotlib
3. Numpy
4. Pandas

1. Loss trend in 1st episode
2. Average loss trend across episodes
3. Reward trend across episodes

• main.py - the main source for project
• qnetwork.py - contains environment, network and experience memory classes.
• utils.py - utility funcitons for states,action,rewards and next states
• dataset - contains realtrace and perfectly correlated data csvs.
• graphical results - stored some results as said above.
• Slides - Slides used for ppt.

• (Activate your tensorflow environment)
• Run python main.py

• Aditya Gulati (ES15BTECH11003)
• Abhinav Gupta (ES15BTECH11002)