Supervised Learning in Multi-Agent Environments Using Inverse Point of View

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F19%3APU132545" target="_blank" >RIV/00216305:26220/19:PU132545 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/8768860" target="_blank" >https://ieeexplore.ieee.org/document/8768860</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TSP.2019.8768860" target="_blank" >10.1109/TSP.2019.8768860</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Supervised Learning in Multi-Agent Environments Using Inverse Point of View

Popis výsledku v původním jazyce

There are many approaches that are being used in multi-agent environment to learn agents’ behaviour. Semisupervised approaches such as reinforcement learning (RL) or genetic programming (GP) are one of the most frequently used. Disadvantage of these methods is they are relatively computational resources demanding, suffers from vanishing gradient during when machine learning approach is used and has often non-convex optimization function, which makes behaviour learning challenging. This paper introduces a method for data gathering for supervised machine learning using agent’s inverse point of view. Proposed method explores agent’s neighboring environment and collects data also from surrounding agents instead of traditional approaches that uses only agents’ sensors and knowledge. Advantage of this approach is, the collected data can be used with supervised machine learning, which is significantly less computationally demanding when compared to RL or GP. A proposed method was tested and demonstrated on Robocode game, where agents (i.e. tanks) were trained to avoid opponent tanks missiles.

Název v anglickém jazyce

Supervised Learning in Multi-Agent Environments Using Inverse Point of View

Popis výsledku anglicky

There are many approaches that are being used in multi-agent environment to learn agents’ behaviour. Semisupervised approaches such as reinforcement learning (RL) or genetic programming (GP) are one of the most frequently used. Disadvantage of these methods is they are relatively computational resources demanding, suffers from vanishing gradient during when machine learning approach is used and has often non-convex optimization function, which makes behaviour learning challenging. This paper introduces a method for data gathering for supervised machine learning using agent’s inverse point of view. Proposed method explores agent’s neighboring environment and collects data also from surrounding agents instead of traditional approaches that uses only agents’ sensors and knowledge. Advantage of this approach is, the collected data can be used with supervised machine learning, which is significantly less computationally demanding when compared to RL or GP. A proposed method was tested and demonstrated on Robocode game, where agents (i.e. tanks) were trained to avoid opponent tanks missiles.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20203 - Telecommunications

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the 2019 42nd International Conference on Telecommunications and Signal Processing (TSP)

ISBN

978-1-7281-1864-2

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

625-628

Název nakladatele

Neuveden

Místo vydání

Neuveden

Místo konání akce

Budapest, Hungary

Datum konání akce

1. 7. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000493442800137