Reinforcement learning (RL) is a rapidly evolving field of machine learning in which autonomous agents learn effective behaviors by interacting with complex, dynamic environments and receiving feedback through reward signals. In our lab, we investigate novel RL algorithms—ranging from deep and graph-relational architectures to noisy network exploration and multi-step prioritized replay—that enable agents to discover optimal decision-making policies under uncertainty and resource constraints. By integrating advanced techniques such as action masking, fairness-aware reward shaping, and convergence detection, we tackle real-world challenges in healthcare scheduling, robotics, and large-scale network optimization. Through theoretical analysis, empirical evaluation, and interdisciplinary collaboration, our goal is to advance RL’s robustness, generalizability, and practical impact across domains where adaptive, data-driven strategies can transform complex decision workflows.

Multimodal machine learning is a subfield of artificial intelligence that aims to build models that can process and relate information from multiple different modalities, such as text, images, audio, and video. The key objective is to create systems that can understand and interpret the world more comprehensively by combining information from different sensory inputs, similar to how humans perceive and understand complex environments.

Computer vision is a field of artificial intelligence that enables computers and systems to derive meaningful information from digital images, videos, and other visual inputs, and act on that information. It involves techniques and models, such as convolutional neural networks, that allow machines to recognize patterns, objects, and attributes in visual data. The applications of computer vision range from facial recognition and autonomous vehicles to medical image analysis and surveillance, significantly impacting various industries and aspects of daily life.

Natural Language Processing (NLP) is a branch of artificial intelligence that focuses on the interaction between computers and humans through natural language, aiming to enable machines to understand, interpret, and generate human languages. It combines computational linguistics—rule-based modeling of human language—with statistical, machine learning, and deep learning models to process and analyze large amounts of natural language data. Applications of NLP are widespread, including language translation, sentiment analysis, chatbots, and voice-activated assistants, significantly enhancing the interface between humans and machines.