AM Turing Award is the tech world’s equivalent of the Nobel prize. It has been awarded this year to two pioneers in the field of reinforcement (RL), Andrew Barto and Richard Sulton. Barto (76) and Sulton (67) did their research on RL since 1970s and paved the way of the past decades AI breaking thoughts.
They channelized the so-called hedonistic machines which could continuously adapt their behaviour in response to positive signals.
It is reinforcement learning (RL) that led a Google computer programme to beat the best human players of the game GO in 2016 and 2017. It is also a key technique to enhance the capability of ChatGPT, optimize the financial trading and helping a robotic hand solve a Rubik’s Cube.
Animal trainers mould the behaviour of dogs and horses. Similarly, RL too moulds the behaviors of machines. They develop AI through RL. This has been recognised formally by declaring a top award to RL scientists.
Leave a Reply