2 papers
cs.RO2026
Composable Model-Free RL for Navigation with Input-Affine Systems
Xinhuan Sang, Abdelrahman Abdelgawad, Roberto Tron
As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time, yet anticipating all possible behaviors is infeasible. We…
cs.LG2025
Closing the Intent-to-Behavior Gap via Fulfillment Priority Logic
Bassel El Mabsout, Abdelrahman Abdelgawad, Renato Mancuso
Practitioners designing reinforcement learning policies face a fundamental challenge: translating intended behavioral objectives into representative reward functions. This challeng…