Variational Inference MPC using Tsallis Divergence

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.

References in corpus (12)

• Superdiffusion and non-Gaussian statistics in a driven-dissipative 2D dusty plasma
• Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
• Asymptotically scale-invariant occupancy of phase space makes the entropy Sq extensive
• Power-Law Distributions for a Trapped Ion Interacting with a Classical Buffer Gas
• Anomalous diffusion and Tsallis statistics in an optical lattice
• Equivalence of the four versions of Tsallis statistics
• Message Passing Stein Variational Gradient Descent
• Alpha-Beta Divergence For Variational Inference
• Tsallis Reinforcement Learning: A Unified Framework for Maximum Entropy Reinforcement Learning
• Stein Variational Model Predictive Control
• Learning Robot Skills with Temporal Variational Inference
• f-Divergence Variational Inference