I'm a Machine Learning Research Fellow with the Army Educational Outreach Program.
- Reinforcement Learning from Human Feedback (RLHF) and Alignment: Specifically focusing on using ratings, as in Rating-Based Reinforcement Learning.
- Natural Language Processing (NLP): I’m actively exploring new research, including the use of LLMs (Large Language Models) in playing Atari games, as in Atari-GPT.
- Atari-GPT: Investigating the capabilities of LLMs as low-level policies in Atari environments. Check out the research here.
- Rating-Based Reinforcement Learning: An alternative to traditional preference based reinforcement learning in which users provide ratings to learn a reward model. Read more about it here.
- Optimal Time-Constrained Intercept Guidance: A project applying deep reinforcement learning to guidance systems. You can explore the paper here.
