Biography
Hi! I’m a Member of Engineering (RL) at Poolside. Prior to this, I have worked at Amazon, Microsoft, and other companies, on research in reinforcement learning (RL), and completed my Ph.D. at Oregon State Universityunder the supervision of Prof. Alan Fern. My research interests span a wide range of RL topics, including explainability of RL agents, model-based RL, planning, offline RL, hierarchical RL, safety of agents, multi-agent RL, and decision/inference-time planning for robotic control and LLM reasoning. Currently, I focus on applying RL and reasoning techniques to improve code generation in large language models (LLMs). If you’re interested in my work or would like to collaborate, feel free to reach out.
- Artificial Intelligence
- Reinforcement Learning
- Planning
- Reasoning
- Abstraction
- Large Language Models
Ph.D. in Computer Science, 2016 - 2022
Oregon State University
Thesis: Investigating Latent State and Uncertainty Representations in Reinforcement Learning
B.E. in Computer Science, 2010 - 2014
University of Mumbai
Experience
- Research and development of reasoning and reinforcement learning for code generation with Large Language Models.
- Research and development of large language models for code generation.
- Research on planning and latent-state representation for reinforcement learning
- Research on safe reinforcement learning for systems
- Research on model-based reinforcement learning for control
- Research on multi-agent reinforcement learning
- Developed full-stack web-products for telecommunication space.
Research Papers
Academic Projects
