I study how reinforcement learning agents generalize to unseen environments — and whether the evaluation protocols the field relies on actually measure what they claim to.

Currently: Senior Data Scientist at Target · Independent RL researcher

Research focus: Generalization in procedurally generated RL environments, with emphasis on evaluation methodology, convergence diagnostics, and architectural inductive biases.

Background: B.Tech in Mechanical Engineering (CS Minor) from IIT Jammu · Director's Gold Medal · RL foundations through independent study (Ravindran, Brunskill) and the ISI Kolkata Winter Schools on Deep Learning (2023, 2025)

• Investigating evaluation methodology and reproducibility in RL generalization benchmarks
• Exploring auxiliary learning objectives (contrastive, self-predictive) for policy generalization in procedural environments
• Manuscripts in preparation — reach out for details

• NTIRE 2022 Challenge on Perceptual Image Quality Assessment · CVPR Workshop (NTIRE) · Paper
• Multi-Scale Features and Parallel Transformers Based Image Quality Assessment · arXiv Preprint · Paper

Portfolio · Google Scholar · LinkedIn · Email