Variational Inference MPC using Tsallis Divergence
This provides a more flexible and effective control framework for robotics applications, though it builds incrementally on prior variational inference MPC methods.
The paper tackles the problem of improving stochastic optimal control performance by developing a generalized variational inference MPC framework using Tsallis divergence, which reduces both mean and variance of control costs across five robotic systems with three policy parameterizations.
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.