Skip to content

Variational Inference MPC using Tsallis Divergence

Authors: Masashi Okada, Tadahiro Taniguchi

Published: 2021 (Conference Paper)

Source: IEEE International Conference on Robotics and Automation (ICRA)

Algorithm: Tsallis VI-SOC

arXiv: 2104.00241

DOI: 10.15607/rss.2021.xvii.073

Summary

Extends variational inference MPC by replacing KL divergence with Tsallis divergence, yielding a broader family of sampling-based controllers that recovers MPPI as a special case and can better handle multimodal cost landscapes.

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 Path Integral Control, Cross Entropy Method, and Stein Variational Inference 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.

Primary

Paper arxiv.org

Standard

arXiv Abstract 2104.00241 arXiv PDF 2104.00241 arXiv HTML 2104.00241 DOI 10.15607/rss.2021.xvii.073

Alternate

roboticsproceedings.org PDF roboticsproceedings.org researchgate.net researchgate.net youtube.com youtube.com

Tags

  • Model predictive path integral control

  • MPPI

  • Variational inference

  • Tsallis divergence

  • Stochastic optimal control

  • Model predictive control