Random Musings

  • Setting up RL experiments with KSP
    How to use KSP's hyper-realistic physics engine as a simulator for RL
    November 26, 2023

  • Computing Fibonacci numbers using Linear Algebra
    Linear Algebra yields a hilariously fast method to compute Fibonacci numbers!
    May 12, 2023

  • My book reviews
    A post about some books that I read recently
    August 28, 2021

  • On Immortality
    Examples in nature that can live forever, and if we humans really aspire that
    July 17, 2021

  • Policy Gradient — some derivations
    Some not-so-obvious derivations of equivalent forms of the policy gradient
    April 2, 2021

  • The Mathematics of Love
    How maths can help find a life partner
    February 14, 2021

  • Lessons from Peter Thiel's book: Zero to One
    Interesting research-relevant lessons from Peter Thiel's notes on startups and building the future
    December 28, 2020

  • Time Travel, Free Will, P vs NP
    Time travel implies no free will, and that P equals NP?
    April 30, 2020

  • Birds are quite 'intelligent'
    A parrot, with a brain the size of a walnut, showed cognitive and linguistic skills matching those of chimps and 5-year old human toddlers.
    January 15, 2020

  • On the Bellman Equation
    The derivation of the Bellman equation is ... subtle.
    July 24, 2019

  • On Variance
    Why is the Bessel's correction required?
    November 24, 2018

  • On Intelligence and AGI
    We keep changing the goalposts for 'intelligence', and it won't be easy to identify 'AGI'.
    September 3, 2018

  • Brilliant article on my guide - Professor B. Ravindran :)
    FactorDaily's coverage of Ravi Sir's background and insights towards AI
    June 4, 2018

  • On the surprising challenges that FAD technology faces.
    We have a long way to go.
    March 22, 2018

  • Summary - DRL doesn't work, yet.
    Key takeaways from an insightful blog.
    February 25, 2018

  • On dinosaurs and arXiv.
    Our greatest ability is adaptation. And we should adapt to making research more accessible.
    February 6, 2018

  • On reward functions.
    Reward functions are tricky to design both in simulations _and_ real life
    January 11, 2018

  • A newfound logolepsy?
    A test of crazy.
    December 7, 2017

  • El Primero
    What? Why?
    October 30, 2017