My interests specifically revolve around reinforcement learning
and robot learning and control (with focus on evolutionary algorithms).
I've worked on a variety of projects relating to programming and machine learning. Some notable examples include jaisalab, a framework for evaluating and developing constrained RL algorithms, and niteshade, a library that facilitates the simulation of cybersecurity attack and defence strategies during online learning. All my projects are available on my GitHub, and below you can find some more examples of my work.
A Python library for simulating data poisoning attack and defence strategies against online machine learning systems. The library is written in Python 3.10 and offers a simple and intuitive API which is heavily integrated with PyTorch's machine learning framework (Developed as part of a group project in my MSc).
A Python framework for developing and evaluating reinforcement learning algorithms that take into account constraints that should be satisfied in OpenAI gym environments, that also provides PyTorch implementations for a few state-of-the-art algorithms in Constrained RL (Developed as part of my MSc Individual Project).
Implemented a simple genetic algorithm that represents color combinations through binary strings and iteratively updates a population of these through mutation and crossover operators based on a fitness function in line with the original games' rules.
Implemented an AI that uses the Minimax algorithm to play a game of Connect 4 optimally by minimizing the maximum losses of any given move. I also implemented the Alpha-beta pruning algorithm which is an alternative on the former that aims to decrease the number of nodes that are evaluated to determine the optimal move.
Designed a parser that structured a set of movie scripts in terms of their indentation levels to identify their dialogues, and subsequently analysed these dialogues to determine if any given movie passed the Bechdel test to different degrees.
Heuristically designed an AI that plays Battleship using Python. Made use of OOP to separate the different aspects of the problem into different modules and objects.
Introduction
Education
Interests
