Modul pro Reinforcment Learning pro Modeler neuronových sítí
| dc.contributor.advisor | Ježek, David | |
| dc.contributor.author | Holaza, Jakub | |
| dc.contributor.referee | Štolfa, Jakub | |
| dc.date.accepted | 2021-06-02 | |
| dc.date.accessioned | 2021-07-15T09:31:05Z | |
| dc.date.available | 2021-07-15T09:31:05Z | |
| dc.date.issued | 2021 | |
| dc.description.abstract | Táto diplomová práca sa zameriava na rozšírenie programu Modeler neurónových sieti o modul pre Reinforcement Learning. V tejto práci je opísaný Reinforcement Learning s a bez použitia hlbokého učenia. Taktiež sú v tejto práci opísané problémy, ktoré Reinforcement Learning má a ich možné riešenia a vylepšenia. V ďalšej časti opisujem paralelizáciu pre Reinforcement Learning s neurónovými sieťami. S využitím implementovaných vylepšení boli vykonané experimenty a porovnaná efektivita učenia. | cs |
| dc.description.abstract | This master thesis focuses on extending the program Neural Net Modeler with Reinforcement Learning module. This thesis describes Reinforcement learning with and without deep learning. Furthermore, this thesis deals with problems of Reinforcement learning and their solutions. Further, I describe the parallelization of Reinforcement learning with neural networks. Using implemented solutions, experiments were performed and results compared. | en |
| dc.description.department | 460 - Katedra informatiky | cs |
| dc.description.result | výborně | cs |
| dc.format.extent | 2564429 bytes | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.other | OSD002 | |
| dc.identifier.sender | S2724 | |
| dc.identifier.thesis | HOL0373_FEI_N2647_2612T025_2021 | |
| dc.identifier.uri | http://hdl.handle.net/10084/144002 | |
| dc.language.iso | cs | |
| dc.publisher | Vysoká škola báňská – Technická univerzita Ostrava | cs |
| dc.rights.access | openAccess | |
| dc.subject | Reinforcement Learning | cs |
| dc.subject | neurónové siete | cs |
| dc.subject | paralelizácia | cs |
| dc.subject | Q-learning | cs |
| dc.subject | DQN | cs |
| dc.subject | Reinforcement Learning | en |
| dc.subject | neural networks | en |
| dc.subject | parallelization | en |
| dc.subject | Q-learning | en |
| dc.subject | DQN | 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 pro Reinforcment Learning pro Modeler neuronových sítí | cs |
| dc.title.alternative | Module Reinforcment Learning for Neuron Net Modeler | en |
| dc.type | Diplomová práce | cs |
Files
Original bundle
1 - 5 out of 5 results
Loading...
- Name:
- HOL0373_FEI_N2647_2612T025_2021.pdf
- Size:
- 2.45 MB
- Format:
- Adobe Portable Document Format
- Description:
- Text práce
Loading...
- Name:
- HOL0373_FEI_N2647_2612T025_2021_zadani.pdf
- Size:
- 47.2 KB
- Format:
- Adobe Portable Document Format
- Description:
- Zadání
Loading...
- Name:
- HOL0373_FEI_N2647_2612T025_2021_priloha.zip
- Size:
- 22.3 MB
- Format:
- Unknown data format
- Description:
- Příloha
Loading...
- Name:
- HOL0373_FEI_N2647_2612T025_2021_posudek_vedouci_Jezek_David.pdf
- Size:
- 55.03 KB
- Format:
- Adobe Portable Document Format
- Description:
- Posudek vedoucího – Ježek, David
Loading...
- Name:
- HOL0373_FEI_N2647_2612T025_2021_posudek_oponent_Stolfa_Jakub.pdf
- Size:
- 54.91 KB
- Format:
- Adobe Portable Document Format
- Description:
- Posudek oponenta – Štolfa, Jakub