TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning

Konstantin Sozykin, Andrei Chertkov, Roman Schutski, ANH-HUY PHAN, Andrzej Cichocki, Ivan Oseledets

Keywords: Black-box, Optimization, Reinforcement Learning, Tensor Train, Cross approximation, Maximum Volume, Quantized networks

Abstract:

We present a novel procedure for optimization based on the combination of efficient quantized tensor train representation and a generalized maximum matrix volume principle.
We demonstrate the applicability of the new Tensor Train Optimizer (TTOpt) method for various tasks, ranging from minimization of multidimensional functions to reinforcement learning.
Our algorithm compares favorably to popular gradient-free methods and outperforms them by the number of function evaluations or execution time, often by a significant margin.