Unmesh Mali

Week 38, 2025

“bas hujum-e-na-umidi (feeling of despair) Khak mein mil jaegi…
ye jo ek lazzat (pleasure) hamari sai-e-be-hasil mein hai – Mirza Ghalib

Having spent the last 2 weeks recovering from the joy, I decided I need to do something different to get on track. That’s why I started meditating this week. I have always had a tumultous relationship with meditation. Even though I am always convinced of its powers to streamline my life, I, for some reason, never do it consistently. I wished to change that starting this week. I meditated almost everyday.


Work

I made considerable progress with my one-click simulation project this week. I am hoping to finish it the next week and hand it over to other folks to play with. This week at work was pleasantly busy (not rushed). I am also part of a group that is helping other colleagues onboard on new AI tools that the company uses. It feels good to be needed and thanked for it.

Projects

Reinforcement Learning

I watched a bunch of YT videos on MDP (Markov Decision Process), Value and Policy Iterations, Bellman’s equation. I am planning to create a grid-world environment, implement policy and value iteration algorithms, and visualize results before this week ends. By the way, I am on month 2 of my RL Learning Plan : RL Learning Plan

Books

Ready Player One - Ernest Cline

Did not read at all!

Fitness

I strongly believe in the Pareto Principle (80/20 rule that says you can get 80% of consequences from 20% of causes). And I believe that a short eating window falls within the 20% of efforts to get good consequences for health. Same thing with Sugar. Cutting out sugar has a huge positive impact on overall health. This line of thinking makes nutrition and fitness slighly easier.

#Weekly-Updates #Reinforcement-Learning #Rl-Level1