Anytime Decoding by Monte-Carlo Tree Search

TL;DR

This paper introduces an anytime decoding algorithm for tree codes using Monte-Carlo tree search, which improves decoding performance with more computational resources and approximates maximum-likelihood decoding.

Contribution

It presents a novel anytime decoding method leveraging Monte-Carlo tree search for tree codes, enabling adjustable complexity-performance trade-offs.

Findings

Decoding performance improves with increased computational time.

The algorithm approximates maximum-likelihood sequence decoding.

Experimental results demonstrate the anytime properties.

Abstract

An anytime decoding algorithm for tree codes using Monte-Carlo tree search is proposed. The meaning of anytime decoding here is twofold: 1) the decoding algorithm is an anytime algorithm, whose decoding performance improves as more computational resource, measured by decoding time, is allowed, and 2) the proposed decoding algorithm can approximate the maximum-likelihood sequence decoding of tree codes, which has the anytime reliability when the code is properly designed. The above anytime properties are demonstrated through experiments. The proposed method may be extended to the decoding of convolutional codes and block codes by Monte-Carlo trellis search, to enable smooth complexity-performance trade-offs in these decoding tasks. Some other extensions and possible improvements are also discussed.