From the 1 of 2 linked papers with an AI index.
2 papers
eess.SY2026
Environment Parameter Gradient Theorem for Policy-Environment Co-Design in Reinforcement Learning
Amber Srivastava
The paper introduces a theorem that provides a formula for how the value function changes with respect to tunable environment parameters, and uses it to create a model‑free algorit…
cs.LG2025
Autonomy-Aware Clustering: When Local Decisions Supersede Global Prescriptions
Amber Srivastava, Salar Basiri, Srinivasa Salapaka
Clustering arises in a wide range of problem formulations, yet most existing approaches assume that the entities under clustering are passive and strictly conform to their assigned…