MPPI is re-derived as EM on a probabilistic optimal control problem, producing a generalized EM-MPPI algorithm with convergence analysis for exponential families and explicit Gaussian cases.
Variational inference mpc using tsallis divergence
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
The authors formulate Tsallis-divergence Fully Probabilistic Design and propose a double-loop fixed-point algorithm, but the contraction proof is invalid and the fixed-point-to-optimality equivalence is unproven.
citing papers explorer
-
Generalized Model Predictive Path Integral Control as Expectation--Maximization
MPPI is re-derived as EM on a probabilistic optimal control problem, producing a generalized EM-MPPI algorithm with convergence analysis for exponential families and explicit Gaussian cases.
-
Towards Tsallis Fully Probabilistic Design
The authors formulate Tsallis-divergence Fully Probabilistic Design and propose a double-loop fixed-point algorithm, but the contraction proof is invalid and the fixed-point-to-optimality equivalence is unproven.