Prashant Trivedi

Thank you for visiting my webpage. I am a post-doctoral scholar at the Department of Computer Science and Engineering (CECS) at the University of Central Florida, USA, working closely with Dr. Amrit Singh Bedi and Prof. George Atia. Before this, I was an ML Scientist at the One Network Enterprises. I have received my Ph.D. from the Industrial Engineering and Operations (IE&OR) department at the Indian Institute of Technology Bombay (IIT Bombay) under the expert supervision of Prof. N. Hemachandra. My research focuses on advancing decision-making under uncertainty, with an emphasis on both theoretical and practical aspects of machine learning, optimization reinforcement learning (RL), multi-agent systems, and AI alignment. Specifically, I am interested in

• Machine Learning: Exploring reinforcement learning (RL), multi-agent reinforcement learning (MARL), deep reinforcement learning, multi-armed bandits.

• Optimization: Investigating problems at the intersection of optimization, stochastic approximation, and AI with human feedback.

• Sequential Decision Making:: Applying various Markov decision process, dynamic programming, stochastic dynamic programming methods for various applications.

• AI Alignment: Addressing challenges in robustness, prompt optimization, safety, reliability within the context of reinforcement learning from human feedback (RLHF).

Email   •   Google Scholar   •   Linkedin   •   CV

Website style cloned from here, here, and here.