A drop in motivation

  • I tested modifications to the Connect 4 training process, without much improvement (or so I thought). I was also frustrated by the limitations imposed by the very slow speed.
  • I worked on a big update to improve speed by running NN model evaluations in parallel, but the work is still in progress.
  • At the beginning of this week, I thought I would take a break from all that, and worked on the game logic for Photosynthesis.

Regaining focus for the end of the challenge

  • Finish the speed optimisation update I started
  • Look at the metrics of the previous training runs, come up with improvements to the training process, and test them
  • Run one last long training session, and test the results (vs. different basic AIs and human players)

My Lee Sedol moment




Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Lunar Testnet Launch with 92 Validators

Vulcan’s suite of conservation projects to join AI2

How Robotic Process Automation (RPA) Will Change the Role of Human Workers

Episode 14: This Person Does Not Exist

A picture is worth a thousand words….what are two billion messages worth?

Everything You Want to Know about AI, but are Afraid To ask

How to Detect Persons on Bicycle, Motor or Scooter?

A Look at Artificial Intelligence and Deep Learning in Chess

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Pierre G.

Pierre G.

More from Medium

Artificial Intelligence : The most potential progress

A picture visualizing future A.I.

AI predictions trending for 2022

How are our addictions and Artificial Intelligence, related?