RockPaperScissors

Machine Learning project which implements Donald Michie’s MENACE methodology for Rock Paper Scissors coded in Java

Machine Learning

A computer program is said to learnn from Experience E with respect to some class of Tasks T and Performance measure P, if its Performance measure P improves in Tasks T with experience E.

MENACE - Machine Educable Noughts and Crosses Engine

Menace was a mechanical computer made from 304 matchboxes built by AI researcher Donald Michie in 1961. It demostrated the learning process by altering the probabilities of events happening.

Rock Paper Scissors

This version of Rock Paper Scissor is an adaptation of original MENACE but with simpler architecture. Rules of the game have been altered to make the Performance measure P easier to judge. In this version of Rock Paper Scissors , player 1 always goes first!!! Now this means player going second should always win! Let’s see if our bot reaches this goal …

Working

• Environment — Physical world in which the agent operates
• State — Current situation of the agent
• Reward — Feedback from the environment
• Policy — Method to map agent’s state to actions
• Value — Future reward that an agent would receive by taking an action in a particular state