Machine Learning with Python Projects - Rock Paper Scissors

Tell us what’s happening:

I am just wondering as Abbey is the only one I can’t get to a 99% accuracy with my player. It usually hovers around 65% accuracy. Is it impossible to get any higher accuracy on Abbey? I’m using both my history and opponents for my model.

Your code so far

Your browser information:

User Agent is: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36

Challenge Information:

Machine Learning with Python Projects - Rock Paper Scissors

1 Like

You’re doing great, keep up the good work! having 65% accuracy against Abbey is already impressive. Abbey is kind of designed to adapt to your move history as it uses an n-gram model, so it’s not just random events. It’s probably reacting to your patterns, 60% is already an achievement.

To improve your score, you can try a few techniques:

  1. Track your last 3+ moves and closely observe how Abbey responds. Then, try to counter what you think Abbey expects you to play.
  2. Now try adding some randomness. For example, play a random move once every 10 rounds to throw off Abbey’s predictions.
  3. Also try starting with random moves instead of predictable ones, then switch to your model after a few rounds when Abbey might begin adapting.

let us know if you have any more questions!