This repository contains an implementation of feedback capacity solution using reinforcement learning as introduced in the paper

The code is compatible with tensoreflow 1.6 environment.

The estimate the capacity of the Ising channel run

python ./main.py --name debug --verbose --env ising --env_cardin 3

• Ziv Aharoni
• Oron Sabag
• Haim Permuter

This project is licensed under the MIT License - see the LICENSE.md file for details