Modul SARSA pro Modeler neuronových sítí
| dc.contributor.advisor | Ježek, David | |
| dc.contributor.author | Mariňák, Tomáš | |
| dc.contributor.referee | Štolfa, Jakub | |
| dc.date.accepted | 2021-06-02 | |
| dc.date.accessioned | 2021-07-15T09:31:06Z | |
| dc.date.available | 2021-07-15T09:31:06Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Táto práca sa zaoberá rozširením programu NeuronNetModeler o ďalší nový modul, ktorý obsahuje reinforcement learning algoritmus SARSA a deep reinforcement learning algoritmus Deep SARSA network. Ďalším jej cieľom je paralelizácia učenia siete Deep SARSA na základe dátovej paralelizácie. V tejto práci sú popísané spomínané algoritmy a ich proces učenia. Ďalej práca obsahuje dátovú paralelizáciu algoritmu Deep SARSA network, ktorá je spúšťaná na distribuovaných uzloch superpočítača. S využitím týchto implementácií boli vykonané experimenty, ktoré sa zameriavali na ich efektivitu a rýchlosť učenia. | cs |
| dc.description.abstract | This master thesis describes extension of the program NeuronNetModeler by new module, that consists of reinforcement learning algorithm SARSA and deep reinforcement learning algorithm called Deep SARSA network. Its next goal is parallelization of Deep SARSA learning based on data parallelization. In this thesis are described already mentioned algorithms and their process of learning. Furthermore this thesis contains data parallelization of Deep SARSA network algorithm, that is runned on distributed nodes of supercomputer. Experiments were done with the usage of this implementation, which were focused on their efficiency and speed of learning process. | en |
| dc.description.department | 460 - Katedra informatiky | cs |
| dc.description.result | výborně | cs |
| dc.format.extent | 2218146 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.other | OSD002 | |
| dc.identifier.sender | S2724 | |
| dc.identifier.thesis | MAR0612_FEI_N2647_2612T025_2021 | |
| dc.identifier.uri | http://hdl.handle.net/10084/144003 | |
| dc.language.iso | cs | |
| dc.publisher | Vysoká škola báňská – Technická univerzita Ostrava | cs |
| dc.rights.access | openAccess | |
| dc.subject | Reinforcement learning | cs |
| dc.subject | SARSA | cs |
| dc.subject | Deep SARSA network | cs |
| dc.subject | Neurónové siete | cs |
| dc.subject | Dátová paralelizácia | cs |
| dc.subject | Reinforcement learning | en |
| dc.subject | SARSA | en |
| dc.subject | Deep SARSA network | en |
| dc.subject | Neural networks | en |
| dc.subject | Data parallelization | en |
| dc.thesis.degree-branch | Informatika a výpočetní technika | cs |
| dc.thesis.degree-grantor | Vysoká škola báňská – Technická univerzita Ostrava. Fakulta elektrotechniky a informatiky | cs |
| dc.thesis.degree-level | Magisterský studijní program | cs |
| dc.thesis.degree-name | Ing. | |
| dc.thesis.degree-program | Informační a komunikační technologie | cs |
| dc.title | Modul SARSA pro Modeler neuronových sítí | cs |
| dc.title.alternative | Module SARSA for Neuron Net Modeler | en |
| dc.type | Diplomová práce | cs |
Files
Original bundle
1 - 5 out of 5 results
Loading...
- Name:
- MAR0612_FEI_N2647_2612T025_2021.pdf
- Size:
- 2.12 MB
- Format:
- Adobe Portable Document Format
- Description:
- Text práce
Loading...
- Name:
- MAR0612_FEI_N2647_2612T025_2021_zadani.pdf
- Size:
- 47.35 KB
- Format:
- Adobe Portable Document Format
- Description:
- Zadání
Loading...
- Name:
- MAR0612_FEI_N2647_2612T025_2021_priloha.zip
- Size:
- 56.64 MB
- Format:
- Unknown data format
- Description:
- Příloha
Loading...
- Name:
- MAR0612_FEI_N2647_2612T025_2021_posudek_vedouci_Jezek_David.pdf
- Size:
- 54.3 KB
- Format:
- Adobe Portable Document Format
- Description:
- Posudek vedoucího – Ježek, David
Loading...
- Name:
- MAR0612_FEI_N2647_2612T025_2021_posudek_oponent_Stolfa_Jakub.pdf
- Size:
- 56.05 KB
- Format:
- Adobe Portable Document Format
- Description:
- Posudek oponenta – Štolfa, Jakub