Open Minded AI: Improving Performance by Keeping All Options on the Table
How I made my Reinforcement Learning agent perform better by making it stop going naively after the highest reward
Published in
6 min readApr 27, 2019
Read this on Medium without being a Medium member using this Friends Link!
The Tic-Tac-Toe game described in this post, as well as all algorithms and pre-trained models can be found on the tic_tac_toe
repository on my GitHub page.