Aysha Sohail

Adaptive-Routing-Agent-Reinforcement-Learning

This project investigates how reinforcement learning agents learn navigation and routing policies under varying reward structures, environment complexity, and training regimes. Rather than optimizing for benchmark performance, the focus is on understanding learning dynamics, stability, and generalization.

Python

LLM-Evaluation-Prompt-Optimization-Playground

A human-in-the-loop LLM evaluation system that turns model outputs into measurable experiments, enabling data-driven optimization of prompts and models.

Python

Large_Scale_Optimization_on_the_VRP_Solution_using_Local_Search_Techniques

This repository contains a Python implementation of a solution to the Vehicle Routing Problem (VRP) using the Variable Neighborhood Descent (VND) methodology.

Fork

crossovers_ga

Experimenting with the the different types of crossovers in genetic algorithm. Please suggest any changes that can help improve the code. Thank you.

Python