Robotics: Science and Systems XVII
Variational Inference MPC using Tsallis Divergence
Ziyi Wang*, Oswin So*, Jason Gibson, Bogdan Vlahov, Manan Gandhi, Guan-Horng Liu, Evangelos Theodorou* These authors contributed equally
Abstract:
In this paper; we provide a generalized framework for Variational Inference-Stochastic Optimal Control by using the non-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.
Bibtex:
@INPROCEEDINGS{WangZ-RSS-21, AUTHOR = {Ziyi Wang AND Oswin So AND Jason Gibson AND Bogdan Vlahov AND Manan Gandhi AND Guan-Horng Liu AND Evangelos Theodorou}, TITLE = {{Variational Inference MPC using Tsallis Divergence}}, BOOKTITLE = {Proceedings of Robotics: Science and Systems}, YEAR = {2021}, ADDRESS = {Virtual}, MONTH = {July}, DOI = {10.15607/RSS.2021.XVII.073} }