English

Variational Inference MPC using Tsallis Divergence

Machine Learning 2021-04-02 v1

Abstract

In this paper, we provide a generalized framework for Variational Inference-Stochastic Optimal Control by using thenon-extensive Tsallis divergence. By incorporating the deformed exponential function into the optimality likelihood function, a novel Tsallis Variational Inference-Model Predictive Control algorithm is derived, which includes prior works such as Variational Inference-Model Predictive Control, Model Predictive PathIntegral Control, Cross Entropy Method, and Stein VariationalInference Model Predictive Control as special cases. The proposed algorithm allows for effective control of the cost/reward transform and is characterized by superior performance in terms of mean and variance reduction of the associated cost. The aforementioned features are supported by a theoretical and numerical analysis on the level of risk sensitivity of the proposed algorithm as well as simulation experiments on 5 different robotic systems with 3 different policy parameterizations.

Keywords

Cite

@article{arxiv.2104.00241,
  title  = {Variational Inference MPC using Tsallis Divergence},
  author = {Ziyi Wang and Oswin So and Jason Gibson and Bogdan Vlahov and Manan S. Gandhi and Guan-Horng Liu and Evangelos A. Theodorou},
  journal= {arXiv preprint arXiv:2104.00241},
  year   = {2021}
}
R2 v1 2026-06-24T00:45:36.319Z