Ocjena učinkovitosti algoritama strojnog učenja unutar simulacijskog okruženja TORCS

master's thesis

• Title (english): Performance evaluation of machine learning algorithms in TORCS simulation environment
• Author: Bruno Torbarina
• Mentor: Domagoj Jakobović (mentor)
• Committee member: Domagoj Jakobović (predsjednik povjerenstva)
• Committee member: Marko Đurasević (član povjerenstva)
• Committee member: Leonardo Jelenković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-07, Croatia

Abstract

U zaključku ovog rada, upoznali smo se sa simulacijskim okruženjem TORCS, istražili različite pristupe strojnom učenju i njihovu primjenu u autonomnoj vožnji. Posebno smo se usredotočili na genetski algoritam i DDPG (Deep Deterministic Policy Gradient) algoritam. Detaljno smo opisali njihovu programsku implementaciju i korištene tehnologije u svrhu ostvarenja ovog rada. Na kraju, iznijeli smo rezultate genetskog algoritma i DDPG algoritma, te smo ih usporedili i procijenili njihovu korisnost za rješavanje ovog problema.

Abstract (english)

In conclusion of this study, we familiarized ourselves with the TORCS simulation environment and explored various machine learning approaches and their application in autonomous driving. We specifically focused on the genetic algorithm and DDPG (Deep Deterministic Policy Gradient) algorithm. We provided detailed insights into their programming implementation and the technologies used to accomplish the objectives of this work. Finally, we presented the results of the genetic algorithm and DDPG algorithm, comparing and evaluating their utility for solving this problem.

• Keywords: Genetski algoritam; DDPG; algoritam; strojno učenje; treniranje; simulacija; vozač; agent; neuronska mreža; model
• Keywords (english): Genetic algorithm; DDPG; algorithm; machine learning; training; simulation; driver; agent; neural network; model
• Language: croatian
• URN:NBN: urn:nbn:hr:168:579098
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 10:48:49