ML project Rock Paper Scissors

Tell us what’s happening:

I don’t understand how to go about this, how is this even an ML project? I need to study the strategy used by the bots and code my own logic to beat them - that beats the entire point of ML if I need to find the pattern.

I wanted to train an LSTM network to predict the next move, but how do I train it? Where do I train it? I can’t train it in player since it is called by the play function. I can’t train it in main, since player won’t know it then. Should I train it elsewhere and somehow hardcode the trained parameters in players? And also the strategy is different for different bots, how do I train a NN to guess the bot and change its strategy? Should I use reinforcement learning?

Very challenging for a beginner who just wants to use Keras to build an AI.

Your code so far

Your browser information:

User Agent is: Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:80.0) Gecko/20100101 Firefox/80.0.

Challenge: Rock Paper Scissors

Link to the challenge:

I decided to just hardcode the logic myself rather than letting a NN figure it out. Steps I took:

  1. Identify which bot we are playing against in the first 3 moves
  2. Reverse engineer code to predict what the next move of the bot will be and beat it

do you know how to beat abbey, that such a good player