2 papers
cs.AI2026
Certificate-Guided Evaluation of Reinforcement Learning Generalization
Vignesh Subramanian, ÄorÄe ŽikeliÄ, Suguman Bansal
This work presents a logic-driven framework to evaluate the performance of reinforcement learning (RL) algorithms in their ability to generalize to unseen tasks. Our framework defi…
cs.AI2026
Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications
Vignesh Subramanian, Subhajit Roy, Suguman Bansal
Inductive generalization is a framework for reinforcement learning (RL) generalization in which inductively related task instances admit inductively related policies. Prior work ca…