Agent-based models (ABMs) are proliferating as decision-making tools across policy areas in transportation, economics, and epidemiology.

Despite its potential, 3DGS encounters challenges such as needle-like artifacts, suboptimal geometries, and inaccurate normals caused by the Gaussians converging into anisotropic shapes with one dominant variance.

Reward Machines provide an automaton-inspired structure for specifying instructions, safety constraints, and other temporally extended reward-worthy behaviour. By exposing the underlying structure of a reward function, they enable the decomposition of an RL task, leading to impressive gains in sample efficiency.

High-stakes prediction tasks (e.g., patient diagnosis) are often handled by trained