About Me

I am currently a Research Fellow in the Army Educational Outreach Program (AEOP), pioneering research in Reinforcement Learning from Human Feedback (RLHF), Alignment and Natural Language Processing. My most recent work primarily focuses on investigating Large Multimodal Language Models capabilities to be used as low-level policies as well as test their visual understanding. We explored these capabilities in different Atari games leading to Atari-GPT, which is currently under review.

One of my most notable contributions is Rating-Based Reinforcement Learning, a new approach that utilizes user ratings to learn reward functions, moving beyond traditional preference-based methods. This innovative work has been recognized and accepted for poster presentations at AAAI 2024 and the Many Facets of Preference-Based Learning workshop at ICML 2023.

In addition I have worked on a project in the realm of path planning. My project, Deep Reinforcement Learning-based Optimal Time-constrained Intercept Guidance, was accepted and presented at the AIAA SciTech Guidance, Navigation, and Control Conference 2024. This research focuses on optimizing intercept guidance systems under stringent time constraints, demonstrating the practical applications of deep reinforcement learning in real-world scenarios.

Beyond my research endeavors, my graduate journey at UTSA has been marked by active participation in various competitions and collaborative projects. I played a pivotal role in the Silent Siren project during the inaugural UTSA Draper Data Science Business Plan Competition, where our team earned honorable mention and bonus awards. By developing a cutting-edge iOS application and edge device model, we innovated a solution to enhance safety for deaf and hard-of-hearing drivers through visual cues for emergency vehicle sirens.

My undergraduate achievements include receiving the Outstanding Undergraduate Award and being part of SDQ Engineering, the team that won the UTSA Tech Symposium 2021. Additionally, participating in the National Science Foundation's Research Experience for Undergraduates program at UTSA ignited my deep interest in artificial intelligence and set the foundation for my current research pursuits.

I am committed to advancing the capabilities of AI through innovative research and interdisciplinary collaboration, aiming to bridge the gap between theoretical advancements and practical implementations. My work strives to contribute to the development of intelligent systems that can understand and interact with the world in increasingly sophisticated ways. Feel free to explore my published works and connect with me on LinkedIn to learn more about my research and professional journey.

Devin White