Problem Statement Suppose you are in a SQUARE playground and a BALL pops up RANDOMLY (but uniformly) in the playground . Your job is to collect the ball and ‘’Wait For The Next Ball’’ to pop up. The next ball pops up after a fixed waiting time only after you collect the…

Stopping RL Agent From Taking Erratic Action Jumps — Introduction One of the biggest challenges for reinforcement learning experts is that they can’t control the agent’s action behavior. Sometimes making the agent converge and maximizing the rewards is not enough, you also want your agent to have smoothened actions. Let’s look at a few examples: Trading In trading, the biggest force…

Mathematically Proving That They are All the Same — Introduction Very often, data scientists and machine learning practitioners don’t appreciate the mathematical and intuitive relationships between different loss metrics like Negative Log Likelihood, Cross Entropy, Maximum Likelihood Estimation, Kullback-Leibler (KL) divergence, and most importantly Mean Square Error. Wouldn’t you be surprised if I say that KL-Divergence and Mean Square Error…

Penning my understanding from the writings of Dr.B.R Ambedkar — Introduction Several studied the tremendous societal, economical and political consequences that “caste problem” inflict on India. It is sometimes seen as a tool for exclusion or as a tool for aggregation. Theoretically, it seems to bring people close overall: it helps improve the cohesiveness amongst groups while increasing the distance between…

Introduction In this blog series, we will learn about classical methods in optimal control which in someway laid a solid foundation for more familiar topics like reinforcement learning. There is an inevitable common boundary between these two fields and this series is aimed to propose these formal methods in optimal control…

Behavioural Cloning, Data Aggregation Approach: DAGGER. — What’s Imitation Learning ? As the same itself suggests, almost every species including humans learn by imitating and also improvise. That’s evolution in one sentence. Similarly we can make machines mimic us and learn from a human expert. …

Price Elasticity, Cross Elasticity and Nash Equilibrium — Contents: 1. Introduction 2. Concept of Elasticity 3. Measuring Elasticity: Linear Regression 4. Example: Data & Code 5. Dynamic Pricing in Competition: Game Theory 6. Nash Equilibrium Introduction One of the biggest challenges in e-commerce is to utilize data mining methods for the improvement of their dynamic pricing policies. Usually these products…

6 -blog series Each less than 5 Minutes — Game Theory: The prelude Intention to write this series of blogs to introduce game theory to readers at an introductory level without requiring…medium.com Game Theory: Story of Thinking In this blog, we will discuss about thinking, which is inevitable process before any decision making. We will lay…kowshikchilamkurthy.medium.com Game Theory: Contention and Cross-Effects We have so far discussed decision problems that a rational individual could face. But as we move more closer to the…kowshikchilamkurthy.medium.com

Continuous actions and Stochastic Strategic Games — Introduction We introduced Nash Equilibrium solution concept in the previous blog. In this blog we will start with a continuous action example and we will discuss the applicability of Nash equilibrium in mixed strategies. Mixed strategies are class of games where player chooses actions stochastically( i.e. …