Still work in progress This project focuses on exploring the research field of dynamic scheduling problems with RL, dealing with stochastic arrival of the new orders and tardiness cost function Main points: Developed the ’Environment’ class using object-oriented programming in Python to address a dynamic scheduling problem, enhancing system flexibility and scalability. Engineered a Reinforcement Learning (RL) agent complete with a customized learning algorithm to efficiently manage dynamic scheduling of orders, accommodating random arrival times and diverse cost functions such as earliness and tardiness.

Github Repo This project focuses on advancing the field of Egocentric Action Recognition through innovative domain adaptation techniques. By leveraging RGB features extracted from the EPIC KITCHEN DATASET with a 3D-inflated network, we explore different domain adaptation methods to enhance generalization across various domain shifts. Our approach combines adversarial learning modules at different temporal aggregation levels with an attentive mechanism and Minimum Class Confusion loss, achieving significant improvements over baseline models.

Github Repo EduQuery is an online learning platform leverages Language Learning Models (LLMs) to create a gamified educational experience. By integrating adaptive learning algorithms, it personalizes content delivery, ensuring that each learner’s journey is unique and engaging. The platform’s interactive challenges and reward systems are designed to increase motivation and enhance retention. With a focus on collaborative learning, users can connect and compete, fostering a community of learners. The use of LLMs not only facilitates language acquisition but also encourages critical thinking and problem-solving skills, making learning both fun and impactful.