Adapting to Changes in Agent Behavior via Finite-Depth Policy Sensitivity

Excerpt

arXiv:2610.07475v1 Announce Type: new Abstract: Adapting a reinforcement learning policy to changes in another agent's behavior typically requires a large amount of new interaction data. Policy sensitivity provides a first-order prediction of how a locally optimal policy changes with a behavioral parameter, but its computation requires second-order derivatives whose effects propagate across future interactions. We develop a finite-depth framework to estimate this sensitivity by approximating the