Symbolic regression in dynamic scenarios with gradually changing targets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00332200" target="_blank" >RIV/68407700:21230/19:00332200 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/19:00332200

Výsledek na webu

<a href="https://doi.org/10.1016/j.asoc.2019.105621" target="_blank" >https://doi.org/10.1016/j.asoc.2019.105621</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.asoc.2019.105621" target="_blank" >10.1016/j.asoc.2019.105621</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Symbolic regression in dynamic scenarios with gradually changing targets

Popis výsledku v původním jazyce

Symbolic regression is a machine learning task: given a training dataset with features and targets, find a symbolic function that best predicts the target given the features. This paper concentrates on dynamic regression tasks, i.e. tasks where the goal changes during the model fitting process. Our study is motivated by dynamic regression tasks originating in the domain of reinforcement learning: we study four dynamic symbolic regression problems related to well-known reinforcement learning benchmarks, with data generated from the standard Value Iteration algorithm. We first show that in these problems the target function changes gradually, with no abrupt changes. Even these gradual changes, however, are a challenge to traditional Genetic Programming-based Symbolic Regression algorithms because they rely only on expression manipulation and selection. To address this challenge, we present an enhancement to such algorithms suitable for dynamic scenarios with gradual changes, namely the recently introduced type of leaf nodes called Linear Combination of Features. This type of leaf node, aided by the error backpropagation technique known from artificial neural networks, enables the algorithm to better fit the data by utilizing the error gradient to its advantage rather than searching blindly using only the fitness values. This setup is compared with a baseline of the core algorithm without any of our improvements and also with a classic evolutionary dynamic optimization technique: hypermutation. The results show that the proposed modifications greatly improve the algorithm ability to track a gradually changing target.

Název v anglickém jazyce

Symbolic regression in dynamic scenarios with gradually changing targets

Popis výsledku anglicky

Symbolic regression is a machine learning task: given a training dataset with features and targets, find a symbolic function that best predicts the target given the features. This paper concentrates on dynamic regression tasks, i.e. tasks where the goal changes during the model fitting process. Our study is motivated by dynamic regression tasks originating in the domain of reinforcement learning: we study four dynamic symbolic regression problems related to well-known reinforcement learning benchmarks, with data generated from the standard Value Iteration algorithm. We first show that in these problems the target function changes gradually, with no abrupt changes. Even these gradual changes, however, are a challenge to traditional Genetic Programming-based Symbolic Regression algorithms because they rely only on expression manipulation and selection. To address this challenge, we present an enhancement to such algorithms suitable for dynamic scenarios with gradual changes, namely the recently introduced type of leaf nodes called Linear Combination of Features. This type of leaf node, aided by the error backpropagation technique known from artificial neural networks, enables the algorithm to better fit the data by utilizing the error gradient to its advantage rather than searching blindly using only the fitness values. This setup is compared with a baseline of the core algorithm without any of our improvements and also with a classic evolutionary dynamic optimization technique: hypermutation. The results show that the proposed modifications greatly improve the algorithm ability to track a gradually changing target.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA15-22731S" target="_blank" >GA15-22731S: Symbolická regrese pro posilované učení ve spojitých prostorech</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Applied Soft Computing

ISSN

1568-4946

e-ISSN

1872-9681

Svazek periodika

2019

Číslo periodika v rámci svazku

83

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

14

Strana od-do

—

Kód UT WoS článku

000488100900015

EID výsledku v databázi Scopus

2-s2.0-85068820262