prikaz prve stranice dokumenta Primjena učenja podrškom na problem dvonožnog hodanja
  Download
PDF 1.96 MB
master's thesis
Primjena učenja podrškom na problem dvonožnog hodanja
Split: University of Split, University of Split, Faculty of science, 2022. urn:nbn:hr:166:932294
Čaleta, Paula
University of Split
Faculty of Science
Department of Mathematics

Institutional repository: Repository of Faculty of Science

Cite this document

Čaleta, P. (2022). Primjena učenja podrškom na problem dvonožnog hodanja (Master's thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:932294

Čaleta, Paula. "Primjena učenja podrškom na problem dvonožnog hodanja." Master's thesis, University of Split, Faculty of Science, 2022. https://urn.nsk.hr/urn:nbn:hr:166:932294

Čaleta, Paula. "Primjena učenja podrškom na problem dvonožnog hodanja." Master's thesis, University of Split, Faculty of Science, 2022. https://urn.nsk.hr/urn:nbn:hr:166:932294

Čaleta, P. (2022). 'Primjena učenja podrškom na problem dvonožnog hodanja', Master's thesis, University of Split, Faculty of Science, accessed 03 December 2024, https://urn.nsk.hr/urn:nbn:hr:166:932294

Čaleta P. Primjena učenja podrškom na problem dvonožnog hodanja [Master's thesis]. Split: University of Split, Faculty of Science; 2022 [cited 2024 December 03] Available at: https://urn.nsk.hr/urn:nbn:hr:166:932294

P. Čaleta, "Primjena učenja podrškom na problem dvonožnog hodanja", Master's thesis, University of Split, Faculty of Science, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:166:932294

Metadata
TitlePrimjena učenja podrškom na problem dvonožnog hodanja
Title (english)Applying reinforcement learning on the bipedal walking problem
AuthorPaula Čaleta
MentorIvo Ugrina (mentor)
Committee memberIvo Ugrina (predsjednik povjerenstva)
Committee memberTanja Vojković (član povjerenstva)
Committee memberDomagoj Jelić (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Mathematics)
Split
Defense date and country2022-07-07, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Cilj je ovog diplomskog rada predstaviti model slobodne metode učenja podrškom primjenjive na rješavanje problema neprekidne kontrole, točnije dvonožnog hodanja. U tu je svrhu prvo opisana struktura i proces učenja neuronskih mreža. Definiramo i osnovne koncepte učenja podrškom, vrste algoritama te dajemo uvid u BipedalWalker-v3 radno okruženje dvonožnog robota u kojem implementiramo algoritme. Zatim prezentiramo TD3 algoritam počevši od DDPG algoritma kao osnove istog te ARS algoritam. Konačno, opisujemo implementaciju u Pythonu i rezultate oba algoritma.
Abstract (english)
The goal of this thesis is to introduce model free reinforcement learning methods applicable on solving continuous control problems, i.e. bipedal walking. For that purpose, the neural networks structure and learning process is first defined. We also define the basic concepts and algorithm types of reinforcement learning and give insight into the BipedalWalker-v3 environment in which we implement the algorithms. Subsequently, we present the TD3 algorithm (starting with the DPPG algorithm as its basis) and the ARS algorithm. Finally, we describe the Python implementation and results of both algorithms.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:932294
Study programmeTitle: Mathematics; specializations in: major in pure mathematics, major in computing, major in teaching, major in statistics and computing
Course: major in computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-07-15 12:07:40