Sökning: "pong"
Visar resultat 6 - 10 av 25 uppsatser innehållade ordet pong.
6. MICRO-ROS FOR MOBILE ROBOTICS SYSTEMS
Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : The complexity of mobile robots increases as more parts are added to the system. Introducing microcontrollers into a mobile robot abstracts and modularises the system architecture, creating a demand for seamless microcontroller integration. LÄS MER
7. Application of Deep Q-learning for Vision Control on Atari Environments
Master-uppsats, Lunds universitet/Beräkningsbiologi och biologisk fysik - Genomgår omorganisationSammanfattning : The success of Reinforcement Learning (RL) has mostly been in artificial domains, with only some successful real-world applications. One of the reasons being that most real-world domains fail to satisfy a set of assumptions of RL theory. LÄS MER
8. Studenters upplevelser av Kungliga Tekniska högskolans digitala lärandemiljö : En explorativ studie
Uppsats för yrkesexamina på avancerad nivå, KTH/LärandeSammanfattning : Utbildning och undervisning har förändrats genom tiderna och många olika redskap har använts. Digitala lärplattformar är ett av dessa redskap. KTH:s lärandemiljö har utvidgats med en digitallärplattform, där Canvas är en del. LÄS MER
9. Co-working in an experiencescape - A case study on the consumption in a co-working space combined with a restaurant and café
Master-uppsats, Göteborgs universitet/Graduate SchoolSammanfattning : The aim of this thesis is to contribute to an understanding of the consumption taking place in a co-working space that is combined with a restaurant and café. The research on such combinations is still sparse and previous literature on co-working and co-working spaces is therefore used in combination with a model which understands physical spaces as experiencescapes. LÄS MER
10. Deep Reinforcement Learning in Cart Pole and Pong
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In this project, we aim to reproduce previous resultsachieved with Deep Reinforcement Learning. We present theMarkov Decision Process model as well as the algorithms Q-learning and Deep Q-learning Network (DQN). We implement aDQN agent, first in an environment called CartPole, and later inthe game Pong. LÄS MER