Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective
Distributional Point-Based Value Iteration (DPBVI), which integrates psi-vectors into a standard point-based backup procedure-bridging DistRL and POMDP planning, lays the foundation for future risk-sensitive control in domains where rare, high-impact events must be carefully managed.
L. Preuett, Qiu-Yi Zhang, Muhammad Ahmad
· 0 citations