Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Understanding Challenges in Reward Function Modeling
Published:
For any of you exploring the field of Reinforcement Learning (RL), I hope this blog is useful in dissecting the various dimensions of Reward Function modeling - the cornerstone of RL.
Research Internship at Imperial Rocketry
Published:
This internship provided an excellent introduction to high-performance computing (HPC) using Julia.
Sulzer Internship - Machine Learning for Damage Inspection in Gas Turbines
Published:
The 2019 internship at Sulzer1 allowed me to apply my machine learning knowledge to the seemingly rigid field of industrial engineering.
Sulzer is one the largest gas turbine maintenance service providers in the world. ↩
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
Utilizing Integral Neural Networks for Imitation Learning
Expected Submission in 2025-01
Utilizing Policy Learning in Integral Form for Imitaiton Learning in Simulated Environments
</article> </div>Robustness To Network Resizing and Catastrophic Interference of Kolmogorov-Arnold and Integral Networks in Imitation Learning
Expected Submission in 2025-01
Examination of Catastrophic Forgetting and Online Resizing in Imitation Learning
</article> </div>research
Using Electric ‘quarter-bridge’ Gauge To Measure Strain
Published:
This is my earliest work from 2018, focusing on using electric strain gauges to analyze the strain and stress characteristics of various materials 1.
The research piece was supervised by Prof. Vito Tagarielli. ↩
Mode Shapes and Dynamic Response of a Structure
Published:
This is my 2018 work on vibration analysis, focusing on the impact of resonant frequencies on structural integrity1.
The research piece was part of the course on Structural Dynamics taught by Prof. Silvestre Taviera Pinho. ↩
Scanning Electron Microscopy of Carbon Fibres
Published:
This is my early 2019 work on failure modes and material loading using Scanning Electron Microscopy (SEM)1.
The research piece was supervised by Prof. Vito Tagarielli. ↩
Designing an Aircraft
Published:
This is my group’s 2019 work on Aircraft Vehicle Design1. Designing an aircraft is a complex task that involves a multi-objective constrained optimization approach.
The research piece was supervised by Prof. Errikos Levis. ↩
Autonomous Drone Delivery - Computer Vision Group
Published:
This is my 2020 work on computer vision applied to autonomous drone delivery1.
The research piece was supervised by Prof. Thulasi Mylvaganam and Prof. Ferri Aliabadi. ↩
Applied Computational Aerodynamics
Published:
This is my 2020 work on applied computational aerodynamics, focusing on the impact of mesh design using Star-CCM+ and AVL for simulation.1
The research piece was part of the course on Applied Computational Aerodynamics taught by Prof. Joaquim Peiro and Prof. Paul Bruce. ↩
Final Year Thesis - Data-driven Hydrodynamic Stability Analysis Using Neural Networks and PCA
Published:
My final year thesis from 2021 explored AI tools for analyzing turbulent flow1.
My thesis was supervised by Prof. Georgios Rigas. ↩
Introduction to Reinforcement Learning - Chapter 1 - Sutton and Barto
Published:
Here I dive into the basics of reinforcement learning (RL) and how it’s all about learning through interaction with the environment to achieve goals by maximizing cumulative rewards.
Exploration and Explotation (Multi-armed Bandits) - Chapter 2 - Sutton and Barto
Published:
Here I focus on the challenge of balancing exploration and exploitation in reinforcement learning (RL), crucial for maximizing cumulative rewards over time. We examined the multi-armed bandit problem as a simplified RL setting where the agent must learn to choose actions (or “arms”) with the best rewards through action-value methods.
Foundations of Robot Motion - Chapter 2 - Lynch and Parker
Published:
Here, in Chapter 2 of Modern Robotics, I explore the concept of a robot’s configuration and degrees of freedom (DoF), crucial for understanding robot motion.
Topology and Representation - Chapter 2 - Lynch and Parker
Published:
In this study I cover concepts from Chapter 2 of Modern Robotics by Lynch and Park, focusing on topology and configuration spaces (C-space) in robotics.
Markov Decision Processes - Chapter 3 - Sutton and Barto
Published:
I explore how Markov Decision Processes (MDPs) extend the framework of bandit problems by incorporating both evaluative feedback and the need for associative actions based on state transitions.
Dynamic Programming (Markov Processes) - Chapter 4 - Sutton and Barto
Published:
In this chapter I dive into how changing time horizon impacts the best strategy in an MDP.
Monte-Carlo Control (Q-learning) - Chapter 5 - Sutton and Barto
Published:
In this chapter I cover Monte Carlo methods, which estimate value functions using sample returns from episodes without needing full knowledge of the environment’s dynamics.
Understanding Q-learning in Reinforcement Learning
Published:
Q-learning is a foundational algorithm in reinforcement learning, designed to help agents discover the optimal strategy for maximizing cumulative rewards in an environment.
Paper Review - Language Instructed Reinforcement Learning for Human-AI Coordination - Paper Review 1
Published:
Here I review Language Instructed Reinforcement Learning for Human-AI Coordination by H. Hu and D. Sadigh.
Model-free Control (TD, MC) - CS234 Lecture 4/Chapter 6
Published:
In this chapter, I study how model-free methods can be paired with policy improvement for control.
Blackjack Policy Evaluation using First-visit Monte Carlo Sampling
Published:
In this post, I explore how a Blackjack strategy can be evaluated using Reinforcement Learning.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Mathematics 1 Teaching Assistant
Undergraduate course, Imperial College London, Department of Aeronautics, 2018
