Comparison of Multiple Reinforcement Learning and Deep Reinforcement Learning Methods for the Task Aimed at Achieving the Goal

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F21%3APU141603" target="_blank" >RIV/00216305:26210/21:PU141603 - isvavai.cz</a>

Výsledek na webu

<a href="https://mendel-journal.org" target="_blank" >https://mendel-journal.org</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.13164/mendel.2021.1.001" target="_blank" >10.13164/mendel.2021.1.001</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Comparison of Multiple Reinforcement Learning and Deep Reinforcement Learning Methods for the Task Aimed at Achieving the Goal

Popis výsledku v původním jazyce

Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) methods are a promising approach to solving complex tasks in the real world with physical robots. In this paper, we compare several reinforcement learning (Q-Learning, SARSA) and deep reinforcement learning (Deep Q-Network, Deep Sarsa) methods for a task aimed at achieving a specific goal using robotics arm UR3. The main optimization problem of this experiment is to find the best solution for each RL/DRL scenario and minimize the Euclidean distance accuracy error and smooth the resulting path by the Bézier spline method. The simulation and real word applications are controlled by the Robot Operating System (ROS). The learning environment is implemented using the OpenAI Gym library which uses the RVIZ simulation tool and the Gazebo 3D modeling tool for dynamics and kinematics.

Název v anglickém jazyce

Comparison of Multiple Reinforcement Learning and Deep Reinforcement Learning Methods for the Task Aimed at Achieving the Goal

Popis výsledku anglicky

Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) methods are a promising approach to solving complex tasks in the real world with physical robots. In this paper, we compare several reinforcement learning (Q-Learning, SARSA) and deep reinforcement learning (Deep Q-Network, Deep Sarsa) methods for a task aimed at achieving a specific goal using robotics arm UR3. The main optimization problem of this experiment is to find the best solution for each RL/DRL scenario and minimize the Euclidean distance accuracy error and smooth the resulting path by the Bézier spline method. The simulation and real word applications are controlled by the Robot Operating System (ROS). The learning environment is implemented using the OpenAI Gym library which uses the RVIZ simulation tool and the Gazebo 3D modeling tool for dynamics and kinematics.

Druh

J_SC - Článek v periodiku v databázi SCOPUS

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název periodika

Mendel Journal series

ISSN

1803-3814

e-ISSN

—

Svazek periodika

27

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

8

Strana od-do

1-8

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85109959286